© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 949
    Prev
    Next
    INDEX
    Explanations

    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
    tiérrez
    -0.59
     spectateurs
    -0.59
    netje
    -0.57
     Glucose
    -0.52
    glycemia
    -0.51
     nød
    -0.49
     glucose
    -0.49
     Stadium
    -0.49
    DeleteBehavior
    -0.49
    Scénario
    -0.48
    POSITIVE LOGITS
     mxArray
    0.62
    pnea
    0.55
    CopyWith
    0.49
    p
    0.48
    antar
    0.47
     Zent
    0.47
     Pyrr
    0.47
     BoxFit
    0.47
    velas
    0.47
    beaten
    0.46
    Activations Density 0.021%

    No Known Activations