© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92885
    Prev
    Next
    INDEX
    Explanations

    technical, legal text

    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
     trattano
    -0.47
     faptul
    -0.41
     disagree
    -0.39
    ništ
    -0.39
     именно
    -0.39
    Personensuche
    -0.38
    umb
    -0.38
     useHistory
    -0.38
    sivu
    -0.38
     svým
    -0.38
    POSITIVE LOGITS
     AssemblyVersion
    0.76
     EClass
    0.66
    存于互联网档案馆
    0.66
     doInBackground
    0.63
    dhury
    0.59
    PositiveButton
    0.59
     propOrder
    0.58
     ویکی‌پدیای
    0.57
    esgue
    0.57
     Закон
    0.56
    Activations Density 0.002%

    No Known Activations