© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92676
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    MessageTagHelper
    -0.60
     and
    -0.52
     both
    -0.49
     још
    -0.46
     separate
    -0.42
     are
    -0.41
     collide
    -0.41
     berdua
    -0.41
     impress
    -0.41
    grà
    -0.41
    POSITIVE LOGITS
    بوابة
    0.86
     فريبيس
    0.73
    Diweddarwch
    0.71
    RectangleBorder
    0.68
     BoxDecoration
    0.68
    BagLayout
    0.68
    bootstrapcdn
    0.62
     Normdatei
    0.62
    VIAF
    0.62
    GEBURTSDATUM
    0.59
    Activations Density 0.001%

    No Known Activations