© 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. 91822
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    :✨
    -0.64
    ModelAdmin
    -0.61
    庁
    -0.59
     initComponents
    -0.59
     resourceCulture
    -0.59
    ніципалі
    -0.58
    EDEFAULT
    -0.58
     CURIAM
    -0.58
     endwhile
    -0.57
     utilisez
    -0.56
    POSITIVE LOGITS
     casais
    0.49
     Enoch
    0.46
    Nek
    0.44
    iastes
    0.43
     laboratories
    0.43
     labs
    0.43
     médicale
    0.43
    logists
    0.43
     /\.(
    0.43
     acci
    0.42
    Activations Density 0.012%

    No Known Activations