© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 376
    Prev
    Next
    INDEX
    Explanations

    hooks and scaffolds

    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
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hooks
    -1.02
     hook
    -1.02
    fer
    -0.94
     scaffold
    -0.90
    FER
    -0.82
     Hook
    -0.78
     HOOK
    -0.73
    hook
    -0.73
    fera
    -0.71
    hooks
    -0.71
    POSITIVE LOGITS
     buurt
    0.68
     Inscrivez
    0.66
     abandonné
    0.66
     financière
    0.62
    inck
    0.60
     Añade
    0.60
     condamné
    0.59
    Przeczytaj
    0.59
     pinulongan
    0.58
    })*/
    0.58
    Activations Density 0.090%

    No Known Activations