© 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. 5-CLT-HP
    7. 360
    Prev
    Next
    INDEX
    Explanations

    News articles and errors

    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
    GeneratedCode
    -0.73
    sizeCache
    -0.67
     nakalista
    -0.65
    省市镇
    -0.64
    ToBounds
    -0.63
    Identyfik
    -0.63
     المعيارى
    -0.62
    findpost
    -0.61
    ⓧ
    -0.60
    WebServlet
    -0.60
    POSITIVE LOGITS
    vering
    0.44
    gameserver
    0.42
    identa
    0.42
    hook
    0.42
    ubar
    0.42
     sea
    0.40
    ônes
    0.39
    game
    0.39
    Obrázky
    0.38
     alcal
    0.38
    Activations Density 0.000%

    No Known Activations