© 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. 71566
    Prev
    Next
    INDEX
    Explanations

    code and formal language

    np_max-act-logits · 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
     BnF
    -0.56
    httphttps
    -0.55
     resourceCulture
    -0.53
    ArgumentParser
    -0.53
    mael
    -0.52
    Carriera
    -0.50
    cheinend
    -0.49
    MLLoader
    -0.48
     CanadaChoose
    -0.47
     angeschlossen
    -0.47
    POSITIVE LOGITS
    الإنجليزية
    0.61
    MigrationBuilder
    0.56
    ⓧ
    0.52
     beginnetje
    0.51
     autorytatywna
    0.51
    ftagPool
    0.51
    routeProvider
    0.50
    omitempty
    0.49
    Portail
    0.49
    IVEREF
    0.48
    Activations Density 0.000%

    No Known Activations