© 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. 20-CLT-HP
    7. 75043
    Prev
    Next
    INDEX
    Explanations

    Code-related

    np_max-act-logits · 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
     WINNER
    -0.79
     recipient
    -0.76
     candidate
    -0.76
     opponent
    -0.74
     winner
    -0.73
     Winner
    -0.72
     participant
    -0.71
     loser
    -0.70
     CANDIDATE
    -0.69
     Candidate
    -0.69
    POSITIVE LOGITS
    rungsseite
    0.79
     للمعارف
    0.64
    GEBURTSDATUM
    0.63
    Lähteet
    0.63
    idopsis
    0.59
     >=",
    0.57
    WriteBarrier
    0.56
     FetchType
    0.56
    interopRequire
    0.56
     DataTypes
    0.56
    Activations Density 0.000%

    No Known Activations