© 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. 5-CLT-HP
    7. 4854
    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
     évêque
    -0.59
    matchCondition
    -0.54
     noten
    -0.54
    RectangleBorder
    -0.54
    ècie
    -0.51
    Biographie
    -0.50
    protoimpl
    -0.49
     prêtres
    -0.49
    Przypisy
    -0.48
     Vikipedi
    -0.48
    POSITIVE LOGITS
     institutions
    0.53
    ########.
    0.51
    sities
    0.49
    rors
    0.48
    Corre
    0.47
    orean
    0.47
    taires
    0.46
    cades
    0.46
     workers
    0.45
    lomer
    0.45
    Activations Density 0.002%

    No Known Activations