© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92411
    Prev
    Next
    INDEX
    Explanations

    .

    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
     تانيه
    -0.80
     myſelf
    -0.71
     Efq
    -0.71
     Monfieur
    -0.68
     itſelf
    -0.64
    Reise
    -0.64
     Jefus
    -0.64
    ⓧ
    -0.63
     Majefty
    -0.60
     Theſe
    -0.60
    POSITIVE LOGITS
     propOrder
    0.56
    </thead>
    0.52
     kaynağından
    0.47
    fillable
    0.44
    ClientRect
    0.43
    WebMethod
    0.42
     method
    0.40
    bilecek
    0.40
    ังก
    0.40
    ColumnHeaders
    0.40
    Activations Density 0.021%

    No Known Activations