© 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. 98030
    Prev
    Next
    INDEX
    Explanations

    sharing

    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
     their
    -0.66
     the
    -0.63
    their
    -0.61
     Their
    -0.61
    Their
    -0.55
     You
    -0.51
    mtable
    -0.50
    ///</
    -0.50
     décid
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     efficiently
    0.68
     effectively
    0.66
     successfully
    0.65
     مرئيه
    0.62
     safely
    0.60
     muualla
    0.60
     profitably
    0.60
     satisfactorily
    0.59
     كومونز
    0.58
     PyQt
    0.57
    Activations Density 0.000%

    No Known Activations