#grad-cam

A convolutional layer has two $2 \times 2$ feature maps $A^1, A^2$. The gradients of the class score $y^c$ (before the softmax) with respect to them are given next to them:

$A^1 = \begin{pmatrix} 1 & 2 \\ 0 & 4 \end{pmatrix}, \quad \frac{\partial y^c}{\partial A^1} = \begin{pmatrix} 0.1 & 0.3 \\ 0.2 & 0.2 \end{pmatrix}, \quad A^2 = \begin{pmatrix} 2 & 0 \\ 1 & 1 \end{pmatrix}, \quad \frac{\partial y^c}{\partial A^2} = \begin{pmatrix} -0.1 & 0.1 \\ -0.2 & -0.2 \end{pmatrix}$

What is the Grad-CAM value at the bottom-right position?