© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

GEMMA-2-2B · 0-CLT-HP · 41022 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
41022

INDEX

Explanations

cutting

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

ReusableCell

-0.97

RetentionPolicy

-0.84

rungsseite

-0.82

 JpaRepository

-0.81

 виправивши

-0.80

parsedMessage

-0.79

IUrlHelper

-0.79

__":

-0.79

elder

-0.76

 Eocene

-0.76

POSITIVE LOGITS

1.21

0.73

ly

0.66

ی

0.65

0.57

0.57

0.56

in

0.56

0.56

ie

0.54

Activations Density 0.217%

No Known Activations