© 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. 0-CLT-HP
    7. 92882
    Prev
    Next
    INDEX
    Explanations

    Money and Cells

    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
     refund
    -0.99
     refunds
    -0.86
     Refund
    -0.85
    cellular
    -0.81
    Refund
    -0.77
     Refunds
    -0.70
    refund
    -0.65
     REFUND
    -0.64
     resourceCulture
    -0.52
     AssemblyCulture
    -0.52
    POSITIVE LOGITS
    AxisAlignment
    0.65
     StringTokenizer
    0.61
    BeginContext
    0.59
     AssemblyVersion
    0.59
    تقاوى
    0.59
     незавершена
    0.57
     وتسجيلات
    0.56
    tonsoft
    0.54
    RectangleBorder
    0.54
     Orrell
    0.54
    Activations Density 0.039%

    No Known Activations