© 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. 1-CLT-HP
    7. 45892
    Prev
    Next
    INDEX
    Explanations

    Euros and code

    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
     cents
    -1.99
     Cents
    -1.24
    cents
    -1.05
     centavos
    -0.76
    cent
    -0.52
     cent
    -0.52
    lorette
    -0.50
    DataSnapshot
    -0.49
    asztal
    -0.49
    /**
    -0.48
    POSITIVE LOGITS
     ویکی‌پدیا
    0.80
     صوتيه
    0.64
     محفوظة
    0.58
     متحده
    0.56
    TintMode
    0.55
    تقاوى
    0.54
    RTLD
    0.54
     EClass
    0.54
    OGND
    0.54
     wireType
    0.54
    Activations Density 0.003%

    No Known Activations