© 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. 5-CLT-HP
    7. 5720
    Prev
    Next
    INDEX
    Explanations

    acety

    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
     SPM
    -0.59
     BSP
    -0.53
     PVA
    -0.52
     useParams
    -0.51
    wps
    -0.50
     FV
    -0.49
     Paglinawan
    -0.47
     lordship
    -0.47
     februarie
    -0.47
     ویکی‌پدی
    -0.46
    POSITIVE LOGITS
    lene
    0.76
     оригіналу
    0.63
    parsedMessage
    0.56
    gensen
    0.54
    nemies
    0.50
    findpost
    0.50
    tent
    0.50
    enumi
    0.49
    getResultList
    0.49
    line
    0.48
    Activations Density 0.001%

    No Known Activations