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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91750
    Prev
    Next
    INDEX
    Explanations

    take

    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
    able
    -0.56
     MainAxisSize
    -0.50
    ais
    -0.50
    ae
    -0.50
    asta
    -0.49
     tass
    -0.48
    eas
    -0.47
    omia
    -0.47
    GIVEREF
    -0.47
    a
    -0.46
    POSITIVE LOGITS
    出版年
    0.73
    Jeografia
    0.65
     héro
    0.59
     nationaux
    0.59
     africains
    0.57
    heureux
    0.56
     médicaux
    0.56
     composizione
    0.55
     miljø
    0.54
    Abp
    0.54
    Activations Density 0.003%

    No Known Activations