© 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. 1-CLT-HP
    7. 787
    Prev
    Next
    INDEX
    Explanations

    names, medicine

    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
     Loomis
    -0.51
     Erickson
    -0.47
     Brewster
    -0.45
     McDowell
    -0.44
    vex
    -0.43
    genstein
    -0.42
    ones
    -0.42
     Ra
    -0.41
    lox
    -0.41
     min
    -0.41
    POSITIVE LOGITS
     InputDecoration
    0.82
    évaluateur
    0.78
    ioutil
    0.75
    gonic
    0.71
    ChildScrollView
    0.71
    DeleteBehavior
    0.70
    WebServlet
    0.69
     useRouter
    0.67
    reportWebVitals
    0.67
    TemporalType
    0.66
    Activations Density 0.089%

    No Known Activations