© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2051
    Prev
    Next
    INDEX
    Explanations

    recently

    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
    pects
    -0.49
    ammans
    -0.47
     trifft
    -0.47
    amaño
    -0.45
    slidesToShow
    -0.44
    !("{}",
    -0.44
    styleUrls
    -0.44
    ?}",
    -0.43
     disponível
    -0.42
     entanto
    -0.41
    POSITIVE LOGITS
    ftagPool
    0.79
    AndEndTag
    0.75
     ModelExpression
    0.72
    BeginContext
    0.68
    Билгалдахарш
    0.66
    parsedMessage
    0.65
    Datuak
    0.64
    PreferredItem
    0.64
    BufferException
    0.61
     announced
    0.60
    Activations Density 0.003%

    No Known Activations