© 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. 40512
    Prev
    Next
    INDEX
    Explanations

    Titles, code

    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
    ugi
    -0.78
     culpa
    -0.62
     step
    -0.49
    leto
    -0.48
     Step
    -0.47
    ji
    -0.45
     West
    -0.44
    lago
    -0.43
    tep
    -0.42
    Go
    -0.42
    POSITIVE LOGITS
     ModelExpression
    1.06
    ImageContext
    0.88
    complexContent
    0.81
     ExecuteAsync
    0.80
    principalColumn
    0.79
    CloseOperation
    0.73
    InSection
    0.72
    DeleteBehavior
    0.72
    +#+#
    0.71
     चीज़ों
    0.71
    Activations Density 0.038%

    No Known Activations