© 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. 90909
    Prev
    Next
    INDEX
    Explanations

    excerpts

    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
     Finnish
    -0.49
     Gare
    -0.46
     SEQ
    -0.44
     French
    -0.44
     Belgian
    -0.44
     thoát
    -0.43
    arischen
    -0.43
    *",
    -0.43
    arische
    -0.42
    agascar
    -0.41
    POSITIVE LOGITS
     виправивши
    0.78
    GEBURTSDATUM
    0.77
    expandindo
    0.73
    EDEFAULT
    0.73
    MigrationBuilder
    0.69
     estekak
    0.68
     betweenstory
    0.68
     дописавши
    0.68
     typelib
    0.64
     فريبيس
    0.62
    Activations Density 0.001%

    No Known Activations