© 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. 72421
    Prev
    Next
    INDEX
    Explanations

    Code and English mix

    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
    endphp
    -0.82
    BeginContext
    -0.82
    migrationBuilder
    -0.77
    Autoritní
    -0.71
    GraphicsUnit
    -0.70
    VersionUID
    -0.68
    AddTagHelper
    -0.67
    colgroup
    -0.66
    SpringRunner
    -0.66
    WriteLiteral
    -0.65
    POSITIVE LOGITS
     handleMessage
    0.42
     josé
    0.38
     jelly
    0.37
    Jelly
    0.37
     Gospel
    0.36
    )=>{
    0.36
    折
    0.36
    Organisateur
    0.35
    josé
    0.35
    badan
    0.35
    Activations Density 0.001%

    No Known Activations