© 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. 45845
    Prev
    Next
    INDEX
    Explanations

    running marathons

    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
    onViewCreated
    -0.73
     Suff
    -0.65
     Thurston
    -0.64
     ویکی‌آمباردا
    -0.62
    WillAppear
    -0.61
    seye
    -0.60
    jago
    -0.60
     calldata
    -0.59
    ItemBackground
    -0.59
    avax
    -0.59
    POSITIVE LOGITS
     into
    0.52
    s
    0.46
    PostInfinity
    0.42
    Hozzáférés
    0.42
    owi
    0.41
     onto
    0.41
     towards
    0.41
    closePath
    0.41
    tig
    0.40
    zilla
    0.40
    Activations Density 0.008%

    No Known Activations