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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74495
    Prev
    Next
    INDEX
    Explanations

    Programming/UI elements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ☸
    -0.49
    AccessorTable
    -0.47
     touristique
    -0.45
    omock
    -0.45
     AssemblyCulture
    -0.45
    ddots
    -0.44
    はじめに
    -0.43
     psicológica
    -0.42
     Corps
    -0.41
    inheritdoc
    -0.41
    POSITIVE LOGITS
     UIImageView
    0.60
     QtCore
    0.59
    Chham
    0.57
    astéroïdes
    0.55
     karakter
    0.52
     character
    0.52
     imageView
    0.52
     Character
    0.51
    Character
    0.51
     player
    0.50
    Activations Density 0.001%

    No Known Activations