© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-2B · 0-CLT-HP · 93967 ｜ Neuronpedia

Home
Gemma-2-2B
0-CLT-HP
93967

INDEX

Explanations

buildings

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

houses

-1.33

 Houſe

-1.17

HOUSE

-1.10

 houſe

-1.10

house

-1.04

thouse

-0.97

thouses

-0.91

 estekak

-0.91

 varandra

-0.91

hauses

-0.90

POSITIVE LOGITS

0.71

0.71

0.70

0.69

0.69

0.69

0.68

ge

0.67

en

0.66

al

0.66

Activations Density 1.335%

No Known Activations