© 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. 6036
    Prev
    Next
    INDEX
    Explanations

    addresses/code/internet

    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
    inn
    -0.52
    acc
    -0.52
    <bos>
    -0.52
    ins
    -0.51
    head
    -0.50
    rest
    -0.50
    re
    -0.49
    self
    -0.49
    bed
    -0.48
    ge
    -0.48
    POSITIVE LOGITS
    webElementXpaths
    0.74
    Hentet
    0.73
    IUrlHelper
    0.72
    VIAF
    0.68
     الحره
    0.63
    MigrationBuilder
    0.63
    uxxxx
    0.60
     GenerationType
    0.59
    PreferredItem
    0.59
     kaynağından
    0.58
    Activations Density 0.003%

    No Known Activations