© 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. 1-CLT-HP
    7. 8985
    Prev
    Next
    INDEX
    Explanations

    water

    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
    principalTable
    -0.71
     aneur
    -0.66
    contentLoaded
    -0.66
    writeFieldEnd
    -0.65
    AccessorTable
    -0.59
    MigrationBuilder
    -0.59
    بوابة
    -0.59
    Хьажоргаш
    -0.58
    الدراسه
    -0.56
    adaptiveStyles
    -0.56
    POSITIVE LOGITS
     value
    0.52
     this
    0.51
     valued
    0.50
    value
    0.50
     Heu
    0.48
    str
    0.48
    bel
    0.47
     púb
    0.46
    data
    0.46
    foreground
    0.45
    Activations Density 0.014%

    No Known Activations