© 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. 5-CLT-HP
    7. 4369
    Prev
    Next
    INDEX
    Explanations

    period

    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
     SafeMath
    -0.71
    +#+#
    -0.71
    InjectAttribute
    -0.71
    #+#
    -0.70
    DockStyle
    -0.69
    InstrumentedTest
    -0.68
    invokeLater
    -0.64
    Demografía
    -0.62
    posedge
    -0.61
     Paglinawan
    -0.61
    POSITIVE LOGITS
     big
    0.53
     level
    0.52
     pro
    0.52
     high
    0.50
     dec
    0.49
     market
    0.49
     re
    0.48
    late
    0.48
    st
    0.48
     heavy
    0.47
    Activations Density 0.007%

    No Known Activations