INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
68.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
mentions of the World Health Organization (WHO)
New Auto-Interp
Negative Logits
Personendaten
-0.36
itinéraires
-0.36
tank
-0.35
bounced
-0.35
replacement
-0.35
replacement
-0.34
kick
-0.34
nutshell
-0.34
finition
-0.33
hates
-0.33
POSITIVE LOGITS
himſelf
0.60
itſelf
0.60
purpoſe
0.59
ſelf
0.57
myſelf
0.56
ſelves
0.55
ValueStyle
0.54
wiſe
0.54
leſs
0.53
ſta
0.52
Activations Density 0.000%