© 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. 9772
    Prev
    Next
    INDEX
    Explanations

    world

    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
     cumplen
    -0.39
    íncipe
    -0.39
     maailman
    -0.38
     siège
    -0.36
     vastaan
    -0.36
     batas
    -0.35
    hlás
    -0.34
    Welt
    -0.34
    ModelSerializer
    -0.34
     zák
    -0.33
    POSITIVE LOGITS
    __*/
    0.90
     يتيمه
    0.79
    abestanden
    0.77
    RectangleBorder
    0.76
    esgue
    0.75
    JspWriter
    0.74
    __(/*!
    0.73
     Roskov
    0.71
    Portály
    0.71
    TintMode
    0.70
    Activations Density 0.057%

    No Known Activations