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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11595
    Prev
    Next
    INDEX
    Explanations

    nine

    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
     MainAxisSize
    -0.71
    MigrationBuilder
    -0.71
    Javadoc
    -0.64
    ubblica
    -0.62
    zeera
    -0.61
    SaveChangesAsync
    -0.61
    nine
    -0.60
    Nine
    -0.58
    */].
    -0.57
    providedIn
    -0.56
    POSITIVE LOGITS
    ous
    0.63
    ties
    0.60
    tious
    0.54
    es
    0.54
    ma
    0.54
    ary
    0.50
    time
    0.49
    teen
    0.48
    teenth
    0.47
    ما
    0.47
    Activations Density 0.010%

    No Known Activations