© 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. 94042
    Prev
    Next
    INDEX
    Explanations

    news sources

    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
     crossorigin
    -0.71
    saraba
    -0.71
     kasarigan
    -0.71
     makeStyles
    -0.71
    ConstraintMaker
    -0.70
     AssemblyCulture
    -0.69
    UserScript
    -0.68
    ftagPool
    -0.66
     CreateTagHelper
    -0.63
    ImageContext
    -0.62
    POSITIVE LOGITS
     pauvres
    0.41
     sû
    0.39
     épaules
    0.39
     piatta
    0.36
    Cyfeiriadau
    0.35
     pattes
    0.35
    AutoScale
    0.35
     malades
    0.35
     samtidig
    0.34
    laris
    0.33
    Activations Density 0.001%

    No Known Activations