© 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. 94595
    Prev
    Next
    INDEX
    Explanations

    "to be" verb

    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
     the
    -0.59
     shouting
    -0.50
     at
    -0.50
     engraçadas
    -0.50
     during
    -0.50
     preſent
    -0.50
     present
    -0.49
     in
    -0.49
     greateſt
    -0.49
     subjective
    -0.48
    POSITIVE LOGITS
    FunctionFlags
    0.66
    ISupport
    0.64
     تضيفلها
    0.60
     Empieza
    0.60
    URLConnection
    0.58
    ècie
    0.57
    ագրություններ
    0.57
     kasarigan
    0.56
    COLN
    0.52
    createCanvas
    0.52
    Activations Density 0.003%

    No Known Activations