© 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. 5-CLT-HP
    7. 511
    Prev
    Next
    INDEX
    Explanations

    medical contexts

    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
    +#+#
    -0.71
    DoubleQuotes
    -0.69
    Geschiedenis
    -0.65
    Executives
    -0.63
     Females
    -0.62
    RenderAtEndOf
    -0.59
    Nuestros
    -0.58
     cref
    -0.58
     officiers
    -0.58
     Lawyers
    -0.57
    POSITIVE LOGITS
     about
    0.78
    about
    0.62
     some
    0.58
    About
    0.56
     up
    0.54
     as
    0.48
     About
    0.47
     
    0.47
     nothing
    0.45
    ถึง
    0.45
    Activations Density 0.002%

    No Known Activations