© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9662
    Prev
    Next
    INDEX
    Explanations

    numerical

    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
     Numerical
    -0.73
    Numerical
    -0.68
    #+#
    -0.66
    InjectAttribute
    -0.66
     للاسماء
    -0.65
    цездатний
    -0.63
    numerical
    -0.60
     通販
    -0.59
     numerical
    -0.57
     חיצוניים
    -0.57
    POSITIVE LOGITS
     Dike
    0.59
    omock
    0.59
    ench
    0.53
     integration
    0.52
    OOTD
    0.50
    ')));
    0.49
    :])
    0.49
     jax
    0.48
     Integration
    0.47
    ítez
    0.46
    Activations Density 0.218%

    No Known Activations