© 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. 3263
    Prev
    Next
    INDEX
    Explanations

    radioactivity

    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
     wears
    -0.57
     is
    -0.52
    とは思
    -0.49
     sits
    -0.49
     sitzt
    -0.48
    τως
    -0.46
    ifikant
    -0.46
     adheres
    -0.43
     does
    -0.43
     eliminates
    -0.42
    POSITIVE LOGITS
    BeginInit
    0.71
    Geplaatst
    0.71
    ArgsConstructor
    0.70
    ņš
    0.66
    })`
    0.66
     فريبيس
    0.62
    InputBorder
    0.61
     समीक्षक
    0.59
     GATE
    0.58
     EconPapers
    0.58
    Activations Density 0.001%

    No Known Activations