© 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. 1-CLT-HP
    7. 15130
    Prev
    Next
    INDEX
    Explanations

    hydro

    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
     Synagogue
    -0.52
     Église
    -0.50
    endosi
    -0.49
     paroisse
    -0.49
    üş
    -0.49
    loride
    -0.48
    romycin
    -0.48
     fermo
    -0.47
    (!__
    -0.47
    ództ
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.72
    المناصب
    0.69
    GenerationType
    0.67
    PreExecute
    0.61
    awtextra
    0.57
    ++];
    0.55
    ";}
    0.54
    djangoproject
    0.52
     makl
    0.52
     doPost
    0.47
    Activations Density 0.048%

    No Known Activations