© 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. 1-CLT-HP
    7. 12377
    Prev
    Next
    INDEX
    Explanations

    diversity

    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
     kasarigan
    -0.76
    MigrationBuilder
    -0.72
    LookAnd
    -0.69
    GEBURTSDATUM
    -0.69
    WithIOException
    -0.67
    PreferredItem
    -0.63
     pinulongan
    -0.63
    ;"></
    -0.61
     snippetHide
    -0.60
    
    -0.60
    POSITIVE LOGITS
     scand
    0.49
    揺
    0.48
    hew
    0.47
    ссию
    0.46
     levels
    0.45
     to
    0.43
     crash
    0.43
     heaviest
    0.43
     terremoto
    0.42
     Kirsch
    0.42
    Activations Density 0.011%

    No Known Activations