© 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. 8671
    Prev
    Next
    INDEX
    Explanations

    istar

    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
    ństwo
    -0.59
    sizeCache
    -0.54
    crania
    -0.52
    
    -0.52
    abar
    -0.52
     incidence
    -0.52
    AxisAlignment
    -0.52
    vaal
    -0.52
    sibility
    -0.51
     publicity
    -0.51
    POSITIVE LOGITS
    ScopeManager
    0.70
     onPostExecute
    0.60
    okovic
    0.55
     ThemeData
    0.52
     connexes
    0.52
     تضيفلها
    0.51
    getDoctrine
    0.50
    Tikang
    0.49
    ingway
    0.49
     Jove
    0.49
    Activations Density 0.174%

    No Known Activations