© 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. 96542
    Prev
    Next
    INDEX
    Explanations

    file information and code

    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
     Zoological
    -0.50
     Opin
    -0.47
     Racial
    -0.46
     ranchers
    -0.45
    Tembelea
    -0.44
    q
    -0.44
    p
    -0.44
    PopupMenu
    -0.44
     Francus
    -0.44
     premature
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.70
    Aktualisiert
    0.66
    isateur
    0.63
    InputBorder
    0.63
    حوالہ
    0.63
    esModule
    0.59
     hâte
    0.59
     مرئيه
    0.58
     Normdatei
    0.58
    Pratique
    0.58
    Activations Density 0.012%

    No Known Activations