INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
71
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
terms related to detective work and criminal investigations
New Auto-Interp
Negative Logits
LabelTagHelper
-0.65
OGND
-0.62
Audiodateien
-0.60
sistors
-0.57
Paglinawan
-0.57
Superhost
-0.55
httphttps
-0.55
AssemblyCulture
-0.53
andExpect
-0.50
himo
-0.50
POSITIVE LOGITS
crime
0.50
CRIME
0.43
crime
0.42
Crime
0.41
0.39
Crime
0.38
homicide
0.36
ValueStyle
0.35
oscu
0.33
vol
0.32
Activations Density 0.000%