© 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. 93531
    Prev
    Next
    INDEX
    Explanations

    Stewart

    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
    ör
    -0.96
     Kee
    -0.66
    Kee
    -0.59
    ÖR
    -0.52
    m
    -0.52
    cy
    -0.51
    ly
    -0.50
    e
    -0.48
    y
    -0.45
    c
    -0.44
    POSITIVE LOGITS
    KommentareTeilen
    0.83
     ModelExpression
    0.82
     myſelf
    0.80
    ^(@)
    0.79
    matchCondition
    0.77
    ⓧ
    0.77
    XmlAccessType
    0.75
    argout
    0.75
    مراجع
    0.75
     ſeveral
    0.74
    Activations Density 0.233%

    No Known Activations