© 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. 0-CLT-HP
    7. 1620
    Prev
    Next
    INDEX
    Explanations

    someone

    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
     figure
    -1.53
    someone
    -1.50
     someone
    -1.40
    Someone
    -1.20
     Someone
    -1.17
    somebody
    -1.12
     SOMEONE
    -1.07
     somebody
    -0.94
    figure
    -0.93
     alguien
    -0.91
    POSITIVE LOGITS
     okuyayım
    0.56
    '
    0.54
     has
    0.53
    IVEREF
    0.52
    hood
    0.50
     تكبرها
    0.50
     acknowledges
    0.49
    ’
    0.49
    ocrat
    0.48
    main
    0.48
    Activations Density 0.037%

    No Known Activations