© 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. 5-CLT-HP
    7. 91428
    Prev
    Next
    INDEX
    Explanations

    of

    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
    tvguidetime
    -0.59
     different
    -0.50
     serez
    -0.50
    ärsk
    -0.49
     surla
    -0.46
    
    -0.45
     gelap
    -0.44
    bedaan
    -0.43
    kirakan
    -0.43
    <bos>
    -0.43
    POSITIVE LOGITS
    Portail
    0.77
    WriteBarrier
    0.69
     оригіналу
    0.66
     tartalomajánló
    0.66
    migrationBuilder
    0.66
     lenker
    0.66
     oprot
    0.66
     actions
    0.63
     SqlDbType
    0.63
    )}</
    0.63
    Activations Density 0.002%

    No Known Activations