© 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. 1901
    Prev
    Next
    INDEX
    Explanations

    archaic language

    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
     period
    -0.91
    ough
    -0.86
     Period
    -0.85
    ought
    -0.83
     Reſ
    -0.80
    period
    -0.77
     Beſ
    -0.77
     Anſ
    -0.77
     Efq
    -0.77
     THOUGH
    -0.75
    POSITIVE LOGITS
    <bos>
    0.88
     to
    0.71
     it
    0.65
     I
    0.65
     for
    0.58
     he
    0.58
     CreateTagHelper
    0.58
     
    0.56
    <eos>
    0.54
     in
    0.53
    Activations Density 0.163%

    No Known Activations