© 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. 4-CLT-HP
    7. 948
    Prev
    Next
    INDEX
    Explanations

    Statistics

    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
    .");
    -0.59
    /");
    -0.54
     */;
    -0.53
    !");
    -0.53
    UnsafeEnabled
    -0.52
    skosten
    -0.50
    °.
    -0.50
    linguistic
    -0.49
    Individual
    -0.48
     bodem
    -0.48
    POSITIVE LOGITS
     require
    0.74
    CppMethod
    0.72
    pexpr
    0.70
     consume
    0.66
     will
    0.66
     occur
    0.64
     begin
    0.63
     respond
    0.63
     undergo
    0.62
     suffer
    0.61
    Activations Density 0.012%

    No Known Activations