© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    sugars/carbohydrates

    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
    @
    -0.47
     Nearly
    -0.39
     tanke
    -0.39
    kk
    -0.37
     They
    -0.37
    ư
    -0.36
    在
    -0.36
    ffi
    -0.35
     speech
    -0.35
     @
    -0.35
    POSITIVE LOGITS
    Autoritní
    0.81
    verwijspagina
    0.81
     المعيارى
    0.79
     ModelExpression
    0.79
     Roskov
    0.75
    Билгалдахарш
    0.74
     วาด
    0.74
    OGND
    0.74
    SourceChecksum
    0.73
    BeginContext
    0.73
    Activations Density 0.002%

    No Known Activations