© 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. 92448
    Prev
    Next
    INDEX
    Explanations

    extension

    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
     extension
    -1.13
     extensions
    -0.97
     channels
    -0.96
    extension
    -0.90
    Extension
    -0.88
     Extension
    -0.78
     Extensions
    -0.77
     Everywhere
    -0.72
     extensión
    -0.71
     EXTENSION
    -0.68
    POSITIVE LOGITS
    AddTagHelper
    0.95
     للاسماء
    0.85
    Tikang
    0.84
     Chwiliwch
    0.81
     ***!
    0.79
    InjectAttribute
    0.78
     متعلقه
    0.77
    BufferException
    0.75
    Дереккөздер
    0.72
    Билгалдахарш
    0.71
    Activations Density 0.292%

    No Known Activations