© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90826
    Prev
    Next
    INDEX
    Explanations

    by

    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
    Negative Logits
    帖最后由
    -0.73
     estimés
    -0.66
     урна
    -0.62
    ineno
    -0.61
    InjectAttribute
    -0.57
    <bos>
    -0.55
     <>",
    -0.54
    FunctionFlags
    -0.53
    Datuak
    -0.52
    TagHelpers
    -0.50
    POSITIVE LOGITS
    LayoutPanel
    0.58
     BorderSide
    0.49
    )$/,
    0.48
     ignorance
    0.45
    MessageTagHelper
    0.45
    readystatechange
    0.44
    ModelAdmin
    0.44
     händ
    0.44
     painless
    0.44
    features
    0.42
    Activations Density 0.009%

    No Known Activations