© 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. 0-CLT-HP
    7. 92839
    Prev
    Next
    INDEX
    Explanations

    events and locations

    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
    i
    -0.70
    er
    -0.66
    ed
    -0.65
    e
    -0.65
    ized
    -0.63
    ist
    -0.62
    ised
    -0.60
    ER
    -0.57
    h
    -0.56
     Diaz
    -0.55
    POSITIVE LOGITS
    RenderAtEndOf
    1.16
    abestanden
    0.96
    WebElementEntity
    0.94
    elemField
    0.89
    parsedMessage
    0.88
    OGND
    0.88
     CreateTagHelper
    0.87
    enterOuterAlt
    0.85
     للمعارف
    0.84
     متعلقه
    0.84
    Activations Density 0.121%

    No Known Activations