© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91116
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Negative Logits
     CreateTagHelper
    -0.80
    LookAnd
    -0.78
     оригіналу
    -0.77
    GEBURTSDATUM
    -0.76
    ✨:
    -0.75
     MainAxisSize
    -0.71
    JspWriter
    -0.71
    Lähteet
    -0.70
     Oldest
    -0.70
     EnglishChoose
    -0.69
    POSITIVE LOGITS
     interesting
    0.56
     great
    0.50
     huge
    0.50
     intriguing
    0.49
     fascinating
    0.48
     impressive
    0.48
     clear
    0.48
     substantial
    0.47
     large
    0.47
     high
    0.47
    Activations Density 0.004%

    No Known Activations