© 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. 94760
    Prev
    Next
    INDEX
    Explanations

    differ

    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
     differs
    -1.02
     differed
    -0.99
     differ
    -0.91
     differential
    -0.89
     distinct
    -0.84
    distinct
    -0.82
    diff
    -0.82
     Differential
    -0.82
     DIFFER
    -0.80
     Distinct
    -0.79
    POSITIVE LOGITS
     ويكيپيديا
    0.75
     lenker
    0.71
     auffi
    0.69
    urably
    0.66
    extAlignment
    0.65
    ſelf
    0.65
     AssemblyCulture
    0.65
    bootstrapcdn
    0.65
    rably
    0.65
     ostavi
    0.64
    Activations Density 0.383%

    No Known Activations