© 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. 20-CLT-HP
    7. 71526
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
    ChildScrollView
    -0.72
    PerformLayout
    -0.69
     SPC
    -0.62
    terbury
    -0.59
    GEBURTSDATUM
    -0.58
    offsetWidth
    -0.57
    principalTable
    -0.57
    reportWebVitals
    -0.57
     RTV
    -0.54
     remarquer
    -0.54
    POSITIVE LOGITS
     pinulongan
    0.61
     skär
    0.47
    ografija
    0.44
    вік
    0.44
    PULL
    0.42
     skolan
    0.42
    increments
    0.41
     regola
    0.40
    ########.
    0.39
     Shand
    0.39
    Activations Density 0.005%

    No Known Activations