© 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. 2563
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
     surla
    -0.74
    XmlAccessorType
    -0.66
    Tembelea
    -0.60
    SequentialGroup
    -0.59
    subpackage
    -0.58
    Ớ
    -0.56
     disambiguazione
    -0.54
    <tbody>
    -0.54
     otomatig
    -0.54
    出版年
    -0.53
    POSITIVE LOGITS
     lenker
    0.69
    Eloquent
    0.54
     mince
    0.49
    ãy
    0.48
     SRS
    0.48
     BeautifulSoup
    0.48
    Malloc
    0.44
     quadrature
    0.43
     WebDriverWait
    0.43
     Avant
    0.43
    Activations Density 0.093%

    No Known Activations