© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 884
    Prev
    Next
    INDEX
    Explanations

    computers and technology

    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
    Билгалдахарш
    -0.68
     فريبيس
    -0.58
    contentLoaded
    -0.57
     كومونز
    -0.56
    ArgsConstructor
    -0.53
     CreateTagHelper
    -0.51
    TintMode
    -0.51
     autorytatywna
    -0.50
    WebVitals
    -0.50
     تضيفلها
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.60
     maailman
    0.58
    RequestParam
    0.57
     catálogo
    0.56
    butuhkan
    0.55
     vnnd
    0.54
    trup
    0.54
     éditoriale
    0.53
    bzero
    0.53
    polation
    0.53
    Activations Density 0.074%

    No Known Activations