© 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. 1868
    Prev
    Next
    INDEX
    Explanations

    as

    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
     rank
    -0.75
     Rank
    -0.70
     as
    -0.63
    ual
    -0.57
     out
    -0.56
    Rank
    -0.54
     to
    -0.54
     ar
    -0.52
    dic
    -0.51
     back
    -0.50
    POSITIVE LOGITS
     jsPsych
    0.91
    🏼
    0.89
     itſelf
    0.85
     myſelf
    0.84
    🏾
    0.82
    <bos>
    0.81
    🏻
    0.81
    ients
    0.77
    🏿
    0.77
    nesses
    0.77
    Activations Density 0.418%

    No Known Activations