INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
57.25
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
terms related to defining, denoting, or referring to concepts in formal or technical contexts
New Auto-Interp
Negative Logits
-0.39
ब्रेकडाउन
-0.36
saraba
-0.36
-0.36
immoral
-0.35
Smol
-0.33
unków
-0.32
Extragalactic
-0.32
unj
-0.31
½
-0.31
POSITIVE LOGITS
LookAnd
0.86
InstrumentedTest
0.72
kasarigan
0.68
'\\;'
0.65
propOrder
0.65
setVerticalGroup
0.65
Италијани
0.63
IsMutable
0.61
AutoScaleMode
0.60
principalTable
0.59
Activations Density 0.008%