© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3688
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ormais
    -0.56
     warung
    -0.48
    GeneratedValue
    -0.48
    áky
    -0.48
     InputDecoration
    -0.47
     jelasnya
    -0.47
    netto
    -0.47
     باخ
    -0.47
    porre
    -0.47
     lär
    -0.47
    POSITIVE LOGITS
    ConstraintMaker
    0.73
    новниш
    0.66
    TintMode
    0.63
    terase
    0.63
    enação
    0.62
     OFDb
    0.62
    хьтан
    0.61
    ContentAsync
    0.58
    ridor
    0.56
    tagHelperRunner
    0.56
    Activations Density 0.003%

    No Known Activations