© 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. 5-CLT-HP
    7. 2864
    Prev
    Next
    INDEX
    Explanations

    information source/guide

    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
    Bảo
    -0.55
     pinulongan
    -0.52
     prossima
    -0.52
    forRoot
    -0.50
    issau
    -0.49
     MainAxisSize
    -0.49
    Impro
    -0.48
     réessayer
    -0.48
     tarko
    -0.48
     comportements
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.63
     specifics
    0.54
     all
    0.54
    ГЛА
    0.53
     specific
    0.53
    Viited
    0.53
     information
    0.53
     for
    0.53
    )}(
    0.52
     requirements
    0.50
    Activations Density 0.005%

    No Known Activations