© 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. 94925
    Prev
    Next
    INDEX
    Explanations

    articles and pronouns

    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
     betweenstory
    -0.68
     even
    -0.56
     даже
    -0.49
     sogar
    -0.47
    ArgumentParser
    -0.47
     навіть
    -0.47
    even
    -0.47
    ControllerTest
    -0.46
    astéroïdes
    -0.46
     ISNI
    -0.45
    POSITIVE LOGITS
    SaveChangesAsync
    0.59
    ardige
    0.57
     trụ
    0.56
     Plain
    0.55
     MainAxisSize
    0.54
     CURIAM
    0.54
     Derfor
    0.54
     OkHttpClient
    0.54
     Beginner
    0.53
     réfrig
    0.53
    Activations Density 0.001%

    No Known Activations