© 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. 97348
    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
     ModelExpression
    -0.88
    ########.
    -0.79
     transfieras
    -0.75
    aarrggbb
    -0.75
     GenerationType
    -0.73
    ConstraintMaker
    -0.71
    fromnode
    -0.71
    ंदीखरीदारी
    -0.67
     cdti
    -0.65
    bootstrapcdn
    -0.65
    POSITIVE LOGITS
     spread
    0.54
     all
    0.50
     jointly
    0.46
     spra
    0.43
    apat
    0.43
     primarily
    0.42
    遍
    0.42
     among
    0.42
     across
    0.42
     distributed
    0.42
    Activations Density 0.001%

    No Known Activations