© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2731
    Prev
    Next
    INDEX
    Explanations

    rules and guidelines

    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
     numerus
    -0.60
    følgelig
    -0.59
     surla
    -0.57
    SharedCtor
    -0.56
    หน้านี้
    -0.53
    ]--;
    -0.52
     يلي
    -0.52
    standard
    -0.52
    standards
    -0.52
    PerformLayout
    -0.52
    POSITIVE LOGITS
    PhysRevD
    0.52
     ویکی‌پدیا
    0.52
     للمعارف
    0.50
    Heya
    0.49
     unless
    0.49
    .
    0.49
    ChromeDriver
    0.48
    Gotta
    0.47
    amsa
    0.47
    ěř
    0.47
    Activations Density 0.003%

    No Known Activations