© 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. 43217
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations

    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
    ecore
    -0.60
     дописавши
    -0.57
    GraphicsUnit
    -0.57
    BindingResult
    -0.56
    yan
    -0.54
    PHPExcel
    -0.54
    eventbus
    -0.54
     оригіналу
    -0.53
    Xna
    -0.52
    tn
    -0.51
    POSITIVE LOGITS
    r
    0.96
    ness
    0.88
    ed
    0.81
    n
    0.78
    ned
    0.73
    ne
    0.71
    s
    0.71
    p
    0.68
    🏻
    0.68
    m
    0.63
    Activations Density 0.072%

    No Known Activations