© 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. 20-CLT-HP
    7. 71603
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     насељу
    -0.79
     Audiodateien
    -0.78
     initComponents
    -0.74
    */].
    -0.70
     незавершена
    -0.68
    abestanden
    -0.67
    UrlResolution
    -0.66
    دانشنامهٔ
    -0.65
    endregion
    -0.65
    >",
    -0.65
    POSITIVE LOGITS
    rdag
    0.38
    bose
    0.38
     ArrayAdapter
    0.37
     تعدى
    0.37
    ellige
    0.36
     Cep
    0.36
     Mino
    0.36
     épo
    0.35
     chal
    0.35
     Domino
    0.35
    Activations Density 0.009%

    No Known Activations