© 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. 20-CLT-HP
    7. 72982
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    np_max-act-logits · 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
    queryInterface
    -0.85
     AssemblyCulture
    -0.70
    WithIOException
    -0.69
     initComponents
    -0.69
    SPATH
    -0.68
    
    -0.68
    errHandler
    -0.67
    execSQL
    -0.67
    رشف
    -0.67
    enumi
    -0.67
    POSITIVE LOGITS
     Polym
    0.44
    äj
    0.40
     vol
    0.40
     دیکھیے
    0.39
     tumb
    0.38
     conven
    0.37
    LayoutStyle
    0.36
    ❞
    0.36
    ANEOUS
    0.36
     cop
    0.35
    Activations Density 0.000%

    No Known Activations