© 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. 0-CLT-HP
    7. 2022
    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
    ArgsConstructor
    -0.74
     незавершена
    -0.72
    corrhi
    -0.59
    σιμοποι
    -0.59
     GoogleFonts
    -0.59
    wur
    -0.58
    TagMode
    -0.58
     Signalez
    -0.58
     propOrder
    -0.58
    "}")
    -0.57
    POSITIVE LOGITS
    adesivo
    0.53
    ValueStyle
    0.53
    AddTagHelper
    0.53
     saites
    0.49
    makeConstraints
    0.48
     Linh
    0.47
     flattered
    0.47
     ORAL
    0.47
     pageContext
    0.47
     وتسجيلات
    0.47
    Activations Density 0.061%

    No Known Activations