© 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. 0-CLT-HP
    7. 92544
    Prev
    Next
    INDEX
    Explanations

    specific topics

    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
    Хьажоргаш
    -0.86
     تكبرها
    -0.78
    Personendaten
    -0.73
     betweenstory
    -0.67
    MLLoader
    -0.66
    ंदीखरीदारी
    -0.66
     kaarangay
    -0.65
     ویکی‌پدی
    -0.61
    Rüyada
    -0.61
     оригіналу
    -0.60
    POSITIVE LOGITS
     cref
    0.59
    runApp
    0.57
     Source
    0.53
    verti
    0.50
     Among
    0.50
     Model
    0.49
     Rie
    0.48
     Time
    0.47
     Ticket
    0.47
     St
    0.47
    Activations Density 2.102%

    No Known Activations