© 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. 97333
    Prev
    Next
    INDEX
    Explanations

    diabetes/glucose

    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
    bv
    -0.44
    ńczy
    -0.44
    ünd
    -0.39
    уда
    -0.39
    Closed
    -0.39
    BV
    -0.39
     breiten
    -0.39
    li
    -0.38
     Closed
    -0.37
    avaient
    -0.37
    POSITIVE LOGITS
    Portail
    0.88
    AsUp
    0.87
    AccessorTable
    0.83
    insulin
    0.83
    Diabetes
    0.81
    AndEndTag
    0.80
    expandindo
    0.79
     diabetics
    0.78
    Insulin
    0.77
     Diabetes
    0.76
    Activations Density 0.004%

    No Known Activations