© 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. 4-CLT-HP
    4. 3432
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    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
    脚注の使い方
    -0.64
     مشين
    -0.57
    pito
    -0.50
     arşivlendi
    -0.49
    XmlAccessType
    -0.47
    ERTE
    -0.46
    fan
    -0.45
     NSCoder
    -0.45
    pensione
    -0.44
    ILLE
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.71
     ModelExpression
    0.68
    yntaxException
    0.67
    MessageTagHelper
    0.63
     my
    0.63
    MLLoader
    0.60
    SqlDataReader
    0.56
    writeField
    0.56
    VIAF
    0.56
    audiovisuel
    0.56
    Activations Density 0.003%

    No Known Activations