© 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. 93029
    Prev
    Next
    INDEX
    Explanations

    scientific/medical terminology

    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
    RenderAtEndOf
    -0.71
     Wikimedijinoj
    -0.69
     AssemblyCulture
    -0.63
    cyklopedia
    -0.63
     CURIAM
    -0.62
    CppCodeGen
    -0.60
    FunctionFlags
    -0.60
    mergeFrom
    -0.58
     onOptions
    -0.57
    LookAnd
    -0.56
    POSITIVE LOGITS
    ochim
    0.56
    .
    0.52
    اعمال
    0.48
     dobu
    0.47
     darb
    0.47
     melakukannya
    0.47
    AutoresizingMask
    0.47
    aticano
    0.45
     ajutor
    0.44
    EDEFAULT
    0.44
    Activations Density 0.108%

    No Known Activations