© 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. 93785
    Prev
    Next
    INDEX
    Explanations

    medical decision-making

    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
     nakalista
    -0.73
     CURIAM
    -0.65
     odkazy
    -0.60
     '.')
    -0.60
    thou
    -0.59
    pherals
    -0.59
     Audiodateien
    -0.59
     linkovi
    -0.59
    WebServlet
    -0.58
    لكتر
    -0.57
    POSITIVE LOGITS
    IContainer
    0.53
     enää
    0.52
     hänen
    0.47
    anguard
    0.45
     ListTile
    0.44
     MyBatis
    0.44
     Sandman
    0.44
     impressions
    0.43
     ролях
    0.42
     neler
    0.42
    Activations Density 0.107%

    No Known Activations