© 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. 72439
    Prev
    Next
    INDEX
    Explanations

    sty/ty

    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
     AttributeSet
    -0.69
    IUrlHelper
    -0.65
    migrationBuilder
    -0.63
    存于互联网档案馆
    -0.61
     referenties
    -0.58
     محفوظة
    -0.58
    tvguidetime
    -0.57
    /*
    -0.56
    LinkId
    -0.56
    ViewFeatures
    -0.56
    POSITIVE LOGITS
    list
    0.53
     esternos
    0.47
    let
    0.47
    rian
    0.46
    ropo
    0.46
     expédi
    0.45
    dee
    0.44
    letek
    0.43
     lijst
    0.43
    tranh
    0.42
    Activations Density 0.003%

    No Known Activations