© 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. 94447
    Prev
    Next
    INDEX
    Explanations

    technical/mechanical

    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
    BrowserModule
    -0.55
     profilo
    -0.51
     Bounty
    -0.50
    createCanvas
    -0.49
    StoryboardSegue
    -0.46
    WebElementEntity
    -0.44
     désolés
    -0.43
     beste
    -0.43
    Ter
    -0.43
     for
    -0.42
    POSITIVE LOGITS
    dymyr
    0.67
    ViewFeatures
    0.61
     <=",
    0.60
    chmal
    0.60
    ConstraintMaker
    0.58
    IDAY
    0.58
    存于互联网档案馆
    0.56
    enumi
    0.56
    AndEndTag
    0.55
     Epilepsy
    0.55
    Activations Density 0.008%

    No Known Activations