© 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. 15060
    Prev
    Next
    INDEX
    Explanations

    cki

    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
    cki
    -1.47
    vaders
    -0.95
     Cranes
    -0.87
     palmar
    -0.77
    nesting
    -0.73
     Roskov
    -0.69
    $​
    -0.68
    DoubleQuotes
    -0.66
     CGPA
    -0.66
    cupa
    -0.66
    POSITIVE LOGITS
    ம்
    0.48
     فريبيس
    0.48
    çoivent
    0.46
    mick
    0.44
    riculum
    0.42
     full
    0.41
     row
    0.41
    loem
    0.41
    sius
    0.40
    neous
    0.40
    Activations Density 0.264%

    No Known Activations