© 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. 4-CLT-HP
    7. 1939
    Prev
    Next
    INDEX
    Explanations

    ational

    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
    ScopeManager
    -0.79
    SourceChecksum
    -0.75
    fycat
    -0.60
    parsedMessage
    -0.56
    ISTRATION
    -0.56
    EndInit
    -0.56
    icom
    -0.55
    DockStyle
    -0.55
    chila
    -0.55
    ly
    -0.55
    POSITIVE LOGITS
     gita
    0.51
     useEffect
    0.49
     rehabilitation
    0.49
    MigrationBuilder
    0.47
     gainera
    0.47
     ACB
    0.46
    TestSuite
    0.44
     Rehabilitation
    0.44
     OBE
    0.44
    aarrggbb
    0.43
    Activations Density 0.006%

    No Known Activations