© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9212
    Prev
    Next
    INDEX
    Explanations

    sausage

    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
     cottura
    -0.47
    uch
    -0.47
     sausage
    -0.44
    <bos>
    -0.44
    Владимир
    -0.43
     borboleta
    -0.42
     Sausage
    -0.42
     soe
    -0.41
    ترك
    -0.40
     Forms
    -0.39
    POSITIVE LOGITS
    CppCodeGen
    0.84
     للاسماء
    0.81
    MigrationBuilder
    0.73
    Carriera
    0.73
     pinulongan
    0.69
    MemoryWarning
    0.67
    interopRequire
    0.66
     lasted
    0.66
     HasFactory
    0.62
    enumii
    0.61
    Activations Density 0.048%

    No Known Activations