© 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. 4-CLT-HP
    7. 1437
    Prev
    Next
    INDEX
    Explanations

    iterations/repetitions within systems

    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
     period
    -0.49
    زال
    -0.45
    period
    -0.45
     propósito
    -0.44
     
    -0.44
     Period
    -0.43
    Period
    -0.42
    '>
    -0.41
    ides
    -0.41
    hemia
    -0.40
    POSITIVE LOGITS
     оригіналу
    0.91
     NSCoder
    0.83
     تضيفلها
    0.80
    BeginContext
    0.80
     الرخصة
    0.73
     '\\;'
    0.71
    __(/*!
    0.70
    WriteBarrier
    0.69
     MainAxisSize
    0.68
     Roskov
    0.68
    Activations Density 0.003%

    No Known Activations