© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13431
    Prev
    Next
    INDEX
    Explanations

    code

    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
     cucchia
    -0.65
    AnchorStyles
    -0.62
     CreateTagHelper
    -0.61
    TagMode
    -0.56
     éti
    -0.56
     Programs
    -0.55
    évaluateur
    -0.54
    aarrggbb
    -0.52
     héri
    -0.52
     vicina
    -0.52
    POSITIVE LOGITS
    <bos>
    0.60
    IsContent
    0.60
     }}$}
    0.54
    MLLoader
    0.53
     legal
    0.53
    География
    0.48
    Vtbl
    0.48
     Popp
    0.47
     SafeMath
    0.47
    geot
    0.46
    Activations Density 0.043%

    No Known Activations