© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93710
    Prev
    Next
    INDEX
    Explanations

    play

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.70
    ThroughAttribute
    -0.69
    outez
    -0.62
    VersionUID
    -0.57
     cref
    -0.50
     HttpNotFound
    -0.50
    EndProject
    -0.49
    hütte
    -0.49
    culoskeletal
    -0.48
    atella
    -0.48
    POSITIVE LOGITS
    <bos>
    0.58
     autorytatywna
    0.57
     يتيمه
    0.53
     Brecht
    0.49
    ClientSize
    0.49
    новниш
    0.48
     lucre
    0.46
     afield
    0.46
     ingrat
    0.46
     Herod
    0.45
    Activations Density 0.017%

    No Known Activations