© 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. 16082
    Prev
    Next
    INDEX
    Explanations

    cover

    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
     Wallflower
    -0.52
    bieron
    -0.49
    mos
    -0.48
    EndContext
    -0.47
    lijker
    -0.45
     kväll
    -0.45
     szerint
    -0.44
     scurt
    -0.44
     gera
    -0.44
    reportWebVitals
    -0.44
    POSITIVE LOGITS
    writeFieldEnd
    0.69
     eventdata
    0.63
    BufferException
    0.63
    providedIn
    0.60
    awtextra
    0.59
    BASEPATH
    0.59
    flink
    0.59
    expandindo
    0.57
    XmlAccessorType
    0.57
     initComponents
    0.56
    Activations Density 0.010%

    No Known Activations