© 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. 5-CLT-HP
    7. 405
    Prev
    Next
    INDEX
    Explanations

    roud

    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
    iltà
    -0.52
    verna
    -0.43
    setof
    -0.42
     apo
    -0.42
     sub
    -0.41
    றை
    -0.40
     enf
    -0.40
     suscep
    -0.40
     Zurück
    -0.39
     sudden
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.91
    BeginContext
    0.77
    jsxFileName
    0.74
    PMailer
    0.74
     <=",
    0.66
     définiti
    0.65
    WebElementEntity
    0.65
    TagHelper
    0.62
     EconPapers
    0.62
     EdgeInsets
    0.61
    Activations Density 0.002%

    No Known Activations