Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11303
    Prev
    Next
    INDEX
    Explanations

    network

    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
     Network
    -0.68
     network
    -0.66
    Datuak
    -0.65
    Network
    -0.63
    bootstrapcdn
    -0.59
    network
    -0.59
     ProtoMessage
    -0.58
    JspWriter
    -0.56
    contentPane
    -0.56
     ویکی‌پدیا
    -0.55
    POSITIVE LOGITS
    ymce
    0.60
    ISupport
    0.58
    initComponents
    0.55
     <<<<<<<<<<<<<<
    0.47
    QMetaType
    0.46
    шив
    0.45
     denominator
    0.44
    umbersome
    0.44
     readme
    0.43
    uper
    0.43
    Activations Density 0.695%

    No Known Activations