© 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. 4-CLT-HP
    7. 2293
    Prev
    Next
    INDEX
    Explanations

    about

    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
     فريبيس
    -0.60
    scalatest
    -0.54
     using
    -0.52
    Hauptartikel
    -0.51
    pagni
    -0.50
     leading
    -0.48
     useRouter
    -0.48
     dominant
    -0.48
     mer
    -0.47
    expandindo
    -0.47
    POSITIVE LOGITS
    SharedDtor
    0.66
     daqui
    0.61
    tangentMode
    0.59
    mybatisplus
    0.58
     kasarigan
    0.55
    पया
    0.55
     démocr
    0.54
     enfans
    0.54
     noDo
    0.54
     âmes
    0.54
    Activations Density 0.003%

    No Known Activations