© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 93133 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
93133

INDEX

Explanations

academic texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Majefty

-0.98

 FetchType

-0.93

 itſelf

-0.91

Efq

-0.91

 ſtate

-0.90

 Monfieur

-0.90

intenance

-0.90

 houſe

-0.88

$_"

-0.86

IBLIO

-0.83

POSITIVE LOGITS

of

0.55

pu

0.53

pel

0.49

0.48

ts

0.46

0.46

↵

0.46

sidemargin

0.45

 suits

0.45

<strong>

0.44

Activations Density 1.540%

No Known Activations