© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 46004
    Prev
    Next
    INDEX
    Explanations

    Code/document snippets

    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
     Discovered
    -0.84
     nakalista
    -0.60
    mphs
    -0.54
     adviser
    -0.52
    onload
    -0.50
     advisers
    -0.48
     dominion
    -0.47
     advisor
    -0.47
    hne
    -0.47
    Reco
    -0.47
    POSITIVE LOGITS
    principalTable
    0.63
    setVerticalGroup
    0.63
     تضيفلها
    0.61
    AnchorStyles
    0.60
     AssemblyTitle
    0.58
    NameInMap
    0.57
     surla
    0.56
    migrationBuilder
    0.56
     uintptr
    0.54
    expandindo
    0.54
    Activations Density 0.005%

    No Known Activations