© 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. 95000
    Prev
    Next
    INDEX
    Explanations

    America/civilizations

    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
     America
    -0.60
     mī
    -0.52
    expand
    -0.47
    ity
    -0.47
    America
    -0.47
     tray
    -0.46
    ade
    -0.45
     ejus
    -0.45
     america
    -0.44
    adem
    -0.44
    POSITIVE LOGITS
    AsUp
    1.02
    s
    0.85
     الرياضيه
    0.83
    LookAnd
    0.80
     beginnetje
    0.79
     kasarigan
    0.79
    VIAF
    0.78
     HasFactory
    0.77
    ArrowToggle
    0.74
    WithIOException
    0.72
    Activations Density 0.618%

    No Known Activations