© 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. 94769
    Prev
    Next
    INDEX
    Explanations

    code/scientific notation

    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
    umper
    -1.88
    zole
    -1.17
    zol
    -0.73
     defaultstate
    -0.59
    ẾT
    -0.56
     esternos
    -0.56
    InBackground
    -0.55
    bietet
    -0.54
    ztő
    -0.53
     getPost
    -0.51
    POSITIVE LOGITS
    Hochspringen
    0.66
    __':
    0.60
     disambiguazione
    0.60
    SourceChecksum
    0.59
    ंदीखरीदारी
    0.54
    Passcode
    0.53
    rrggbb
    0.52
    ASX
    0.52
    MathML
    0.50
    TypedDataSet
    0.50
    Activations Density 0.054%

    No Known Activations