© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94597
    Prev
    Next
    INDEX
    Explanations

    Smith

    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
     Smith
    -2.47
    Smith
    -2.44
     smith
    -2.36
     SMITH
    -2.23
    SMITH
    -1.79
    smith
    -1.72
     Smiths
    -1.70
    mith
    -1.25
    smithy
    -0.91
     Smit
    -0.82
    POSITIVE LOGITS
    s
    1.24
    ies
    0.74
     AssemblyCulture
    0.71
    ی
    0.71
     CURIAM
    0.69
    soda
    0.66
    ers
    0.64
    AddTagHelper
    0.64
    sail
    0.62
    ships
    0.60
    Activations Density 0.014%

    No Known Activations