© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 2002
    Prev
    Next
    INDEX
    Explanations

    fissure

    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
    s
    -0.79
    y
    -0.68
    e
    -0.67
     SEDS
    -0.60
     Италијани
    -0.59
    yntaxException
    -0.59
    sat
    -0.59
    ship
    -0.58
    sc
    -0.56
    ing
    -0.56
    POSITIVE LOGITS
    Czytaj
    0.75
    WEET
    0.73
     ویکی‌پدیای
    0.71
     raiſ
    0.68
     Efq
    0.66
    Kjelder
    0.65
     itſelf
    0.64
     myſelf
    0.62
     Houſe
    0.61
    슷
    0.61
    Activations Density 0.087%

    No Known Activations