INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
55
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
patterns of punctuation and formatting in the text
New Auto-Interp
Negative Logits
<<<<<<<<<<<<<<
-0.35
fertiliser
-0.34
switch
-0.32
nawr
-0.31
hakim
-0.31
),),
-0.30
Wylie
-0.30
AndFlush
-0.30
Lo
-0.29
bootloader
-0.29
POSITIVE LOGITS
kasarigan
0.72
betweenstory
0.65
ſelf
0.65
AsUp
0.63
purpoſe
0.61
LEGGI
0.60
ſta
0.58
Infórmanos
0.58
queſta
0.57
+#+#
0.57
Activations Density 1.217%