© 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. 5-CLT-HP
    7. 6122
    Prev
    Next
    INDEX
    Explanations

    Numbers and codes

    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
    wnież
    -0.53
     Potosí
    -0.51
     Obrador
    -0.51
    haraan
    -0.50
     correctes
    -0.50
     שוליים
    -0.50
    PhysRev
    -0.50
    úgó
    -0.49
    öscht
    -0.49
    loroethane
    -0.49
    POSITIVE LOGITS
    archiviato
    0.64
     Hodg
    0.57
    ftagPool
    0.54
     Benav
    0.50
     nonatomic
    0.50
     doInBackground
    0.49
     ゆ
    0.48
    ICULO
    0.48
    SCORE
    0.47
    참고
    0.47
    Activations Density 0.001%

    No Known Activations