© 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. 14437
    Prev
    Next
    INDEX
    Explanations

    building

    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
    NOPQRST
    -0.59
     springfox
    -0.56
    /');
    -0.48
    omod
    -0.47
    /')
    -0.46
    yonel
    -0.45
    ciatore
    -0.45
    KommentareTeilen
    -0.45
    sheng
    -0.45
     \%}$
    -0.45
    POSITIVE LOGITS
     autorytatywna
    0.73
    project
    0.67
     ModelExpression
    0.65
     CURIAM
    0.62
     propios
    0.60
    Project
    0.60
     terpisah
    0.58
    ásban
    0.57
    spoiler
    0.56
     comigo
    0.56
    Activations Density 0.021%

    No Known Activations