INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
33.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
technical terms and notation related to formulas and mathematical expressions
New Auto-Interp
Negative Logits
retudo
-0.38
nawr
-0.36
cucharadita
-0.35
bubuk
-0.34
reszcie
-0.34
WireFormat
-0.32
<bos>
-0.30
пожалуйста
-0.29
tagext
-0.29
preocupes
-0.28
POSITIVE LOGITS
propOrder
0.66
rrggbb
0.65
0.63
setVerticalGroup
0.62
évaluateur
0.60
betweenstory
0.60
transQ
0.59
purpoſe
0.57
Искәрмәләр
0.54
TemporalType
0.54
Activations Density 3.420%