© 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. 606
    Prev
    Next
    INDEX
    Explanations

    been

    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
     to
    -0.81
     répondu
    -0.75
     bakgrund
    -0.65
     dentaire
    -0.61
     abstrait
    -0.61
     abandonné
    -0.60
     fallu
    -0.59
     allmän
    -0.59
     regardé
    -0.57
     igång
    -0.56
    POSITIVE LOGITS
    TagMode
    0.68
    OGND
    0.61
    SourceChecksum
    0.56
    AndEndTag
    0.54
    verwijspagina
    0.53
    ("}");
    0.53
     raving
    0.53
     виправивши
    0.52
    astify
    0.52
     насељу
    0.52
    Activations Density 0.005%

    No Known Activations