© 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. 1-CLT-HP
    7. 14131
    Prev
    Next
    INDEX
    Explanations

    marginal

    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
     marginal
    -2.09
    marginal
    -2.00
     Marginal
    -1.99
    Margin
    -1.20
     marginalized
    -0.96
     marginally
    -0.86
    :✨
    -0.84
    CppCodeGen
    -0.77
     pinulongan
    -0.77
    margin
    -0.76
    POSITIVE LOGITS
     Delia
    0.46
    isten
    0.43
    lero
    0.43
     casualty
    0.43
    COMMA
    0.42
     Availability
    0.41
    asic
    0.41
    kew
    0.41
     ke
    0.41
     AspNetCore
    0.41
    Activations Density 0.046%

    No Known Activations