© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2027
    Prev
    Next
    INDEX
    Explanations

    at

    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
    ArgsConstructor
    -0.67
     مرئيه
    -0.59
    about
    -0.58
    ￣)
    -0.55
     OrderedDict
    -0.49
     Swit
    -0.49
     eight
    -0.49
     only
    -0.47
     about
    -0.47
     seven
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
     通販
    0.59
    jsxFileName
    0.57
     home
    0.57
    ècie
    0.56
     OFDb
    0.56
     trường
    0.54
    省市镇
    0.53
    verwijspagina
    0.53
     it
    0.53
    Activations Density 0.003%

    No Known Activations