© 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. 0-CLT-HP
    7. 95325
    Prev
    Next
    INDEX
    Explanations

    purpo

    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
     purpo
    -0.75
     урна
    -0.62
     censiti
    -0.57
    <&
    -0.55
     CreateTagHelper
    -0.54
    doria
    -0.53
    ImageField
    -0.52
    moine
    -0.52
     đu
    -0.52
    <?,
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.68
     ExecuteAsync
    0.59
    rrggbb
    0.57
     nakalista
    0.55
     kaynağından
    0.51
    uitable
    0.49
    สึก
    0.48
    الإنجليزية
    0.48
    xaml
    0.48
    Билгалдахарш
    0.47
    Activations Density 1.286%

    No Known Activations