© 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. 20-CLT-HP
    7. 73522
    Prev
    Next
    INDEX
    Explanations

    code, names, abbreviations

    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
    DockStyle
    -0.76
     Мексичка
    -0.70
    twimg
    -0.67
    IntoConstraints
    -0.62
     CreateTagHelper
    -0.61
    úgó
    -0.61
    ソッド
    -0.60
     MainAxisSize
    -0.59
    WriteBarrier
    -0.57
    styleType
    -0.57
    POSITIVE LOGITS
     La
    0.74
     Lat
    0.74
    La
    0.63
     Marquis
    0.61
     Tre
    0.60
     Qu
    0.60
     Ras
    0.59
     Asia
    0.58
     Tame
    0.57
    Lat
    0.57
    Activations Density 0.000%

    No Known Activations