© 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. 11414
    Prev
    Next
    INDEX
    Explanations

    Arundel

    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
    chter
    -2.50
    chte
    -0.96
    chten
    -0.90
    cter
    -0.70
    chtete
    -0.63
    GraphicsUnit
    -0.61
    DeleteBehavior
    -0.58
    EndGlobalSection
    -0.57
     sink
    -0.56
    +#+#
    -0.56
    POSITIVE LOGITS
     noqa
    0.57
    页面存档备份
    0.54
    lectic
    0.52
     Devonshire
    0.50
    tonsoft
    0.48
     virgen
    0.48
    Daz
    0.47
    冗
    0.47
    packer
    0.47
    mechanical
    0.47
    Activations Density 0.006%

    No Known Activations