© 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 · 93464 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
93464

INDEX

Explanations

wicket

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

XmlAccessType

-0.75

mybatisplus

-0.72

SBATCH

-0.68

 uintptr

-0.58

 typelib

-0.58

 ProtoMessage

-0.57

WebElementEntity

-0.57

 Мексичка

-0.57

 ModelExpression

-0.57

-0.56

POSITIVE LOGITS

1.40

ed

1.30

1.27

er

1.07

1.00

0.97

0.91

es

0.86

 Theſe

0.83

ee

0.83

Activations Density 1.755%

No Known Activations