© 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. 91909
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
     juſ
    -0.50
     Jefus
    -0.49
     onyx
    -0.46
     Chriftian
    -0.46
     willow
    -0.44
     houſe
    -0.43
     Compañía
    -0.42
     Cæsar
    -0.42
     Efq
    -0.42
    sApp
    -0.41
    POSITIVE LOGITS
     Strain
    0.77
     Disorder
    0.73
     Contamin
    0.71
     Virus
    0.70
     Hormone
    0.68
     Acid
    0.68
     Syndrome
    0.68
     Dysfunction
    0.67
     Infection
    0.67
     Disease
    0.67
    Activations Density 0.005%

    No Known Activations