© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10901
    Prev
    Next
    INDEX
    Explanations

    ms

    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
     landowners
    -0.55
    lizes
    -0.53
    OptionsMenu
    -0.50
     leksikon
    -0.50
    <bos>
    -0.50
     jScrollPane
    -0.49
     smelt
    -0.49
     BMP
    -0.48
    oli
    -0.48
    oi
    -0.47
    POSITIVE LOGITS
     समीक्षाओं
    0.72
     estekak
    0.65
     AssemblyCulture
    0.61
    ьаж
    0.60
     للمعارف
    0.59
    GNUC
    0.57
     مشين
    0.57
    PreferredItem
    0.57
    fromCharCode
    0.56
    Спасылкі
    0.54
    Activations Density 0.089%

    No Known Activations