© 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. 4996
    Prev
    Next
    INDEX
    Explanations

    White

    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
    AccessorTable
    -0.68
    úgó
    -0.64
    Tracce
    -0.52
     selectors
    -0.52
     canali
    -0.49
     băr
    -0.49
    inguém
    -0.48
    LinkId
    -0.48
     Cristo
    -0.48
    addCriterion
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.71
     Houſe
    0.59
    CloseOperation
    0.57
     LoggerFactory
    0.56
     House
    0.55
    AnchorStyles
    0.55
     BoxDecoration
    0.52
    ertz
    0.52
    logeny
    0.50
    页面存档备份
    0.50
    Activations Density 0.001%

    No Known Activations