© 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. 0-CLT-HP
    7. 92846
    Prev
    Next
    INDEX
    Explanations

    magnify

    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
    󠁿
    -0.73
    migrationBuilder
    -0.72
     للمعارف
    -0.70
     nahilalakip
    -0.66
    WebVitals
    -0.65
    IDAD
    -0.64
    GRAPHY
    -0.63
     amplify
    -0.63
     imageNamed
    -0.63
    rikes
    -0.63
    POSITIVE LOGITS
     Reſ
    0.97
     Houſe
    0.96
     ſche
    0.92
     pleaſure
    0.92
     Conſ
    0.91
     houſe
    0.91
     itſelf
    0.90
     purpoſe
    0.86
     Diſ
    0.84
     Chriftian
    0.84
    Activations Density 0.233%

    No Known Activations