© 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. 12408
    Prev
    Next
    INDEX
    Explanations

    import

    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
     BoxFit
    -0.85
     uintptr
    -0.77
     propOrder
    -0.72
    RetentionPolicy
    -0.71
    RuleContext
    -0.69
     newBuilder
    -0.68
     елның
    -0.68
     '\\;'
    -0.63
     Мексичка
    -0.63
     Italijanski
    -0.62
    POSITIVE LOGITS
    קישורים
    0.56
    HasForeignKey
    0.55
     Chalmers
    0.52
     Nye
    0.49
    '
    0.47
    omi
    0.46
    ONE
    0.46
     Dank
    0.46
     bons
    0.46
    Datagram
    0.45
    Activations Density 2.343%

    No Known Activations