© 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. 43912
    Prev
    Next
    INDEX
    Explanations

    playlist

    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
    fully
    -0.75
    hik
    -0.63
    avas
    -0.54
    yel
    -0.54
    nov
    -0.52
    hii
    -0.50
    hia
    -0.50
    amb
    -0.49
    reas
    -0.48
     américains
    -0.48
    POSITIVE LOGITS
    )_/¯
    0.96
     resourceCulture
    0.93
    NameInMap
    0.91
     betweenstory
    0.79
     صوتيه
    0.77
    parsedMessage
    0.77
    IUrlHelper
    0.71
    :✨
    0.69
     kasarigan
    0.69
    SourceChecksum
    0.68
    Activations Density 0.099%

    No Known Activations