© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    article/verb "to be"

    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
     Roskov
    -0.55
    hésite
    -0.53
    licky
    -0.49
    .’”
    -0.48
     Egyptians
    -0.48
    cioni
    -0.48
     DialogResult
    -0.46
     Mitar
    -0.46
     Sprecher
    -0.46
    FFECT
    -0.45
    POSITIVE LOGITS
    <bos>
    0.67
     MainAxisSize
    0.67
     الحره
    0.60
    DotNetBar
    0.55
     nonatomic
    0.54
     lenker
    0.51
     חיצוניים
    0.50
    mybatisplus
    0.50
    their
    0.49
    migrationBuilder
    0.49
    Activations Density 0.022%

    No Known Activations