© 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. 94403
    Prev
    Next
    INDEX
    Explanations

    staffing

    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
     Jepang
    -0.56
    tow
    -0.48
     remplacé
    -0.46
    Rol
    -0.45
     fallu
    -0.45
    精
    -0.45
    vig
    -0.45
    둘
    -0.44
     Vig
    -0.44
     Vigil
    -0.43
    POSITIVE LOGITS
    ContentAsync
    0.75
     AssemblyCulture
    0.73
     дописавши
    0.69
    OrBuilder
    0.69
    EndTag
    0.67
    uxxxx
    0.67
    naments
    0.63
     >=",
    0.63
    ⓧ
    0.63
    msgTypes
    0.62
    Activations Density 0.097%

    No Known Activations