© 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. 90483
    Prev
    Next
    INDEX
    Explanations

    structure

    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
     structure
    -2.36
    structure
    -1.89
     Structure
    -1.77
    Structure
    -1.70
     structures
    -1.45
     STRUCTURE
    -1.45
     estructura
    -1.40
     struktur
    -1.34
     Struktur
    -1.33
    STRUCTURE
    -1.33
    POSITIVE LOGITS
    parsedMessage
    0.82
     médicale
    0.79
     vermelhas
    0.77
     régionale
    0.76
     للمعارف
    0.76
     Савезне
    0.75
    ništvo
    0.74
     CreateTagHelper
    0.74
    AddHtmlAttribute
    0.73
     vectorielle
    0.73
    Activations Density 0.137%

    No Known Activations