Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-2-2B
2-RES-MATRYOSHKA-DC
8
Prev
Next
MODEL
2-res-matryoshka-dc
Source/SAE
INDEX
Go
Explanations
mathematical expressions involving inequalities, limits, and equations
oai_token-act-pair · gpt-4.1-nano
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/2-res-matryoshka-dc/8?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/2-res-matryoshka-dc/8?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
in
-0.69
for
-0.63
es
-0.58
ten
-0.56
has
-0.56
’
-0.56
can
-0.55
ago
-0.54
is
-0.53
two
-0.53
POSITIVE LOGITS
>=</
1.93
/=
1.91
=
1.81
:=
1.72
)=
1.70
=
1.70
}=
1.69
|=
1.66
)]=
1.59
$=
1.55
Act
ivations
Density 7.258%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
