© 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. 97408
    Prev
    Next
    INDEX
    Explanations

    healthcare

    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
     useAppContext
    -0.66
    دانشنامهٔ
    -0.58
    Geplaatst
    -0.54
     referenties
    -0.53
     ویکی‌پدیای
    -0.50
     незавершена
    -0.47
    <bos>
    -0.45
    ślę
    -0.45
     ivelany
    -0.44
     comigo
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.79
    AccessorTable
    0.66
    BorderFactory
    0.63
     (“
    0.57
     '{@
    0.56
    IVEREF
    0.54
    lès
    0.54
    protoimpl
    0.54
    CppMethod
    0.52
    jooq
    0.52
    Activations Density 0.092%

    No Known Activations