© 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. 4-CLT-HP
    7. 1036
    Prev
    Next
    INDEX
    Explanations

    reports and studies

    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
    NameInMap
    -0.62
     للمعارف
    -0.56
    SourceChecksum
    -0.55
     ostavi
    -0.54
     више
    -0.48
    ValueStyle
    -0.48
    __.__
    -0.45
     resourceCulture
    -0.45
    SuspendLayout
    -0.45
    webElementXpaths
    -0.43
    POSITIVE LOGITS
     on
    0.73
    findpost
    0.70
    <bos>
    0.68
    ніципалі
    0.68
     stål
    0.66
    corazón
    0.65
    Бахар
    0.62
     klokken
    0.60
    ikistan
    0.59
     BoxDecoration
    0.59
    Activations Density 0.005%

    No Known Activations