© 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. 5-CLT-HP
    7. 3524
    Prev
    Next
    INDEX
    Explanations

    can

    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
     الرياضيه
    -1.12
    GEBURTSDATUM
    -1.00
    ItemBackground
    -0.96
     AssemblyTitle
    -0.95
     Мексичка
    -0.91
    AndroidJUnit
    -0.90
    EndProject
    -0.88
    ConstraintMaker
    -0.88
    SharedDtor
    -0.88
    AsUp
    -0.87
    POSITIVE LOGITS
     leher
    0.31
     یا
    0.31
     or
    0.31
    ابد
    0.30
     bulun
    0.30
     sahiptir
    0.28
     compromis
    0.28
    áct
    0.28
    到底
    0.27
     letti
    0.27
    Activations Density 0.019%

    No Known Activations