© 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. 4802
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    makeConstraints
    -0.73
     obé
    -0.61
    xpress
    -0.50
     makeStyles
    -0.49
    atég
    -0.49
    CppMethod
    -0.48
     terci
    -0.48
    cstring
    -0.48
    valget
    -0.47
    geordnet
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.77
    InputTagHelper
    0.59
    ).</
    0.57
    )");
    0.55
    XmlEnum
    0.54
    tvguidetime
    0.54
     мәкал
    0.54
    NUMX
    0.54
    eriksaan
    0.54
    >",
    0.54
    Activations Density 0.003%

    No Known Activations