© 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. 4-CLT-HP
    7. 1330
    Prev
    Next
    INDEX
    Explanations

    Groceries and shopping

    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
    dem
    -0.57
    demo
    -0.56
    points
    -0.54
     derivative
    -0.54
    param
    -0.52
     '\\;'
    -0.52
    AFM
    -0.52
    Demo
    -0.51
     Demonstration
    -0.51
     Demo
    -0.50
    POSITIVE LOGITS
    TagMode
    0.59
    ReusableCell
    0.56
    BeginContext
    0.52
     SqlDbType
    0.49
    ところです
    0.49
    Hochspringen
    0.47
     متحده
    0.47
    例文帳に追加
    0.46
     surla
    0.46
     propOrder
    0.45
    Activations Density 0.002%

    No Known Activations