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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96162
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    itself
    -0.73
     itself
    -0.60
     épaules
    -0.54
     Itself
    -0.50
     tartalmaz
    -0.50
     dégâts
    -0.48
     proprement
    -0.47
     vœux
    -0.47
    himself
    -0.46
     dimaksud
    -0.46
    POSITIVE LOGITS
     propOrder
    0.64
    InitVars
    0.63
    ьаж
    0.59
     متعلقه
    0.59
    AntiForgeryToken
    0.59
    DataContract
    0.58
     <=",
    0.57
    arXiv
    0.57
    encodeWith
    0.56
     AssemblyProduct
    0.55
    Activations Density 0.003%

    No Known Activations