© 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. 8884
    Prev
    Next
    INDEX
    Explanations

    generate

    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
    DockStyle
    -0.75
    InputBorder
    -0.68
    viewDidLoad
    -0.65
    migrationBuilder
    -0.60
     initComponents
    -0.59
    ScopeManager
    -0.58
    ChildScrollView
    -0.57
     flesta
    -0.57
    decks
    -0.55
    Geplaatst
    -0.54
    POSITIVE LOGITS
    OCCURRED
    0.48
    TRIBUN
    0.45
    olas
    0.45
     laying
    0.45
     arose
    0.44
    कार
    0.43
    ist
    0.43
     cysts
    0.42
     rospy
    0.42
     substances
    0.42
    Activations Density 0.020%

    No Known Activations