© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1476
    Prev
    Next
    INDEX
    Explanations

    sight

    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
     оригіналу
    -0.47
    مصادر
    -0.47
    Décès
    -0.46
    허
    -0.45
    таратура
    -0.44
     nahilalakip
    -0.44
     berço
    -0.43
    حياته
    -0.43
     cuna
    -0.43
    atimes
    -0.42
    POSITIVE LOGITS
     of
    0.86
     parseFrom
    0.64
    ValueStyle
    0.59
    Notae
    0.59
     useParams
    0.56
    UrlResolution
    0.55
    ManagedBean
    0.54
    posedge
    0.52
     emitted
    0.51
     <>",
    0.50
    Activations Density 0.006%

    No Known Activations