© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8806
    Prev
    Next
    INDEX
    Explanations

    syna

    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
    Negative Logits
    //
    -0.66
     twelve
    -0.50
    principalColumn
    -0.49
     Fourteen
    -0.48
     initComponents
    -0.48
     reed
    -0.48
    AttributeSet
    -0.47
    räger
    -0.46
    <bos>
    -0.46
    OFF
    -0.45
    POSITIVE LOGITS
    Демографія
    0.62
     Walkover
    0.56
     GenerationType
    0.56
    енча
    0.55
    SourceChecksum
    0.52
     bescha
    0.49
     geha
    0.49
    itinéraire
    0.48
     utbild
    0.48
    ēju
    0.47
    Activations Density 0.044%

    No Known Activations