© 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. 1330
    Prev
    Next
    INDEX
    Explanations

    immune responses and antigens

    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
     everything
    -0.83
     whatever
    -0.79
     tudo
    -0.65
    everything
    -0.61
    bin
    -0.56
    ERY
    -0.53
     apapun
    -0.53
    whatever
    -0.52
    ery
    -0.51
     allt
    -0.50
    POSITIVE LOGITS
    a
    0.79
    ly
    0.76
    ا
    0.68
    alse
    0.64
    ///</
    0.64
    t
    0.63
    else
    0.62
    aire
    0.62
     $_"
    0.61
    ‟
    0.61
    Activations Density 0.777%

    No Known Activations