© 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. 98255
    Prev
    Next
    INDEX
    Explanations

    number

    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
     checks
    -0.53
     Paglinawan
    -0.49
    lini
    -0.46
    はじめに
    -0.46
     breakthroughs
    -0.46
     check
    -0.45
     schedules
    -0.44
    impresa
    -0.44
    checks
    -0.44
    check
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.63
     المعيارى
    0.57
    hland
    0.54
     jScrollPane
    0.54
     poils
    0.54
    estinal
    0.53
    URIComponent
    0.53
    adpleegd
    0.52
     lèvres
    0.52
    IGENCE
    0.52
    Activations Density 0.003%

    No Known Activations