© 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. 45533
    Prev
    Next
    INDEX
    Explanations

    Technical internet content

    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
    はじめに
    -0.75
    ioutil
    -0.56
     habitudes
    -0.54
    Искәрмәләр
    -0.51
    riwal
    -0.51
     Olympus
    -0.50
    ruptedException
    -0.49
    ilarities
    -0.49
    nastics
    -0.49
    BufferException
    -0.49
    POSITIVE LOGITS
    writeFieldEnd
    0.68
     contextLoads
    0.65
     Exacts
    0.56
     Stays
    0.56
    ंदीखरीदारी
    0.55
     ligiloj
    0.54
    تقاوى
    0.54
    expandindo
    0.54
     ***!
    0.53
     Stead
    0.52
    Activations Density 0.079%

    No Known Activations