© 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. 5-CLT-HP
    7. 96994
    Prev
    Next
    INDEX
    Explanations

    Actions and functions

    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
     CreateTagHelper
    -0.74
     للاسماء
    -0.68
    ApiException
    -0.68
     will
    -0.67
     StatefulWidget
    -0.62
    حياته
    -0.62
    nior
    -0.60
     خواهد
    -0.60
    Spoljašnje
    -0.59
     بيها
    -0.58
    POSITIVE LOGITS
     once
    0.94
    once
    0.81
    Once
    0.72
     Once
    0.67
    ONCE
    0.66
     ONCE
    0.64
    Should
    0.55
     should
    0.54
     Should
    0.52
    should
    0.51
    Activations Density 0.012%

    No Known Activations