© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45491
    Prev
    Next
    INDEX
    Explanations

    invoices

    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
     itſelf
    -1.61
     Efq
    -1.49
    ſelves
    -1.46
     Houſe
    -1.41
     Monfieur
    -1.41
     Reſ
    -1.36
     Diſ
    -1.35
    ſelf
    -1.34
     Jefus
    -1.34
     Theſe
    -1.33
    POSITIVE LOGITS
    i
    0.83
    o
    0.78
    ing
    0.76
    y
    0.73
     in
    0.67
     we
    0.65
    ed
    0.64
     
    0.63
     (
    0.63
     and
    0.62
    Activations Density 0.064%

    No Known Activations