© 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. 10321
    Prev
    Next
    INDEX
    Explanations

    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
    interopRequire
    -0.71
     resourceCulture
    -0.70
    ⓧ
    -0.64
     createState
    -0.57
    ########.
    -0.57
    AnchorStyles
    -0.57
    webElementXpaths
    -0.55
    <?
    -0.54
     OnInit
    -0.54
    EndInit
    -0.54
    POSITIVE LOGITS
    emos
    0.73
    eky
    0.54
    osha
    0.52
    ">—
    0.51
    ists
    0.51
    ope
    0.50
    etto
    0.49
    opy
    0.49
    DotNet
    0.49
    copg
    0.49
    Activations Density 0.017%

    No Known Activations