© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    dys

    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
    TagMode
    -0.63
     part
    -0.60
    łaś
    -0.59
    yka
    -0.58
     storm
    -0.56
    sety
    -0.56
     Zwie
    -0.56
     draft
    -0.55
     yeast
    -0.54
     faſt
    -0.54
    POSITIVE LOGITS
    mappedBy
    0.47
     stället
    0.45
    gonic
    0.43
    abaikan
    0.43
    UrlResolution
    0.43
     varandra
    0.43
    Rüyada
    0.42
    mybatisplus
    0.41
     deportivas
    0.41
     exemplaires
    0.40
    Activations Density 0.006%

    No Known Activations