© 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. 1-CLT-HP
    7. 9396
    Prev
    Next
    INDEX
    Explanations

    tralight

    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
    tralight
    -1.17
    textit
    -0.42
    drucks
    -0.40
     RCP
    -0.38
     Rost
    -0.37
    logits
    -0.35
    któ
    -0.35
     Ronald
    -0.35
    ghest
    -0.34
    pula
    -0.34
    POSITIVE LOGITS
    دانشنامهٔ
    0.84
    principalColumn
    0.79
     defaultstate
    0.77
     EconPapers
    0.77
     فريبيس
    0.77
    帖最后由
    0.75
    LookAnd
    0.75
    juana
    0.75
    place
    0.75
    webElementXpaths
    0.74
    Activations Density 0.155%

    No Known Activations