© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1691
    Prev
    Next
    INDEX
    Explanations

    Bran Stark (Game of Thrones)

    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
    ymo
    -1.41
    
    -0.97
    muth
    -0.89
    Diwedd
    -0.86
    endphp
    -0.81
    MigrationBuilder
    -0.81
    PerformLayout
    -0.80
     صوتيه
    -0.76
    RetentionPolicy
    -0.75
    Gambas
    -0.74
    POSITIVE LOGITS
    ig
    0.56
    ons
    0.53
    T
    0.52
    i
    0.51
     dis
    0.50
    ign
    0.50
     direct
    0.50
     T
    0.49
    ля
    0.48
    ol
    0.47
    Activations Density 0.363%

    No Known Activations