© 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. 20-CLT-HP
    7. 77873
    Prev
    Next
    INDEX
    Explanations

    sickness

    np_max-act-logits · 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
     kasarigan
    -0.69
     CURIAM
    -0.54
     botines
    -0.45
    acri
    -0.44
    IntoConstraints
    -0.44
    انيف
    -0.43
    žel
    -0.43
    STYLE
    -0.43
    Freedom
    -0.43
     chaqueta
    -0.42
    POSITIVE LOGITS
     ovary
    0.61
    Geplaatst
    0.61
     sickness
    0.60
     Sick
    0.60
     asthma
    0.60
     sickle
    0.59
    Rhestr
    0.59
     ovaries
    0.57
     testis
    0.57
     esophagus
    0.56
    Activations Density 0.025%

    No Known Activations