© 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. 38364
    Prev
    Next
    INDEX
    Explanations

    imported

    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
    ating
    -1.29
    ATING
    -0.82
    ing
    -0.73
    cing
    -0.62
     imported
    -0.60
    iah
    -0.59
    selling
    -0.55
     er
    -0.50
    uring
    -0.50
    ming
    -0.50
    POSITIVE LOGITS
     GenerationType
    0.98
    IUrlHelper
    0.95
    +#+#
    0.95
     незавершена
    0.94
    abestanden
    0.87
    Diweddarwch
    0.87
    RenderAtEndOf
    0.87
    Geplaatst
    0.86
     nahilalakip
    0.85
     ProtoMessage
    0.84
    Activations Density 0.595%

    No Known Activations