© 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. 14662
    Prev
    Next
    INDEX
    Explanations

    Anatomy or medical procedures

    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
    :✨
    -0.56
    forName
    -0.48
    NOPQRST
    -0.47
    ensement
    -0.44
    ########.
    -0.44
     취
    -0.44
     fidé
    -0.43
    閑
    -0.43
     Pflanze
    -0.43
    bed
    -0.42
    POSITIVE LOGITS
     bezeichneter
    0.73
    ⓧ
    0.65
    routeProvider
    0.62
    Портал
    0.59
     arşivlendi
    0.57
     ligiloj
    0.56
    ;';
    0.56
     Приступљено
    0.56
     autorytatywna
    0.55
    Personendaten
    0.55
    Activations Density 0.017%

    No Known Activations