© 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. 0-CLT-HP
    7. 43413
    Prev
    Next
    INDEX
    Explanations

    jobs,processes

    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
     ran
    -0.60
     runs
    -0.59
     Runs
    -0.45
    y
    -0.45
     single
    -0.43
     supervisor
    -0.43
     garanzia
    -0.42
     radiated
    -0.42
    Supervisor
    -0.40
    րա
    -0.40
    POSITIVE LOGITS
    évaluateur
    0.98
     betweenstory
    0.96
     itſelf
    0.95
    ьаж
    0.93
    TypedDataSet
    0.88
    
    0.85
     myſelf
    0.85
    WithIOException
    0.83
    protoimpl
    0.79
    MigrationBuilder
    0.79
    Activations Density 0.044%

    No Known Activations