© 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. 5-CLT-HP
    7. 2738
    Prev
    Next
    INDEX
    Explanations

    origins or beginnings

    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
     first
    -0.71
    Билгалдахарш
    -0.69
     indisponible
    -0.55
     först
    -0.52
     впервые
    -0.52
    first
    -0.49
     or
    -0.49
     kasarigan
    -0.47
    webElementXpaths
    -0.46
     primeros
    -0.46
    POSITIVE LOGITS
     houſe
    0.63
    存于互联网档案馆
    0.60
    istiques
    0.60
     ſame
    0.59
     Bantu
    0.58
     Bonjour
    0.58
    Бы
    0.57
    ått
    0.57
     dacia
    0.57
     Epile
    0.57
    Activations Density 0.006%

    No Known Activations