© 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. 97383
    Prev
    Next
    INDEX
    Explanations

    Aaron

    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
     Aaron
    -1.86
    Aaron
    -1.71
    aaron
    -0.75
     Aar
    -0.68
    araoh
    -0.55
    idic
    -0.54
    rophes
    -0.49
    дії
    -0.48
    tură
    -0.47
    gemäß
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.79
    ImageContext
    0.71
    mybatisplus
    0.70
     Beatrix
    0.70
    OGND
    0.68
     viewWillAppear
    0.68
     Efq
    0.68
     myſelf
    0.66
    HtmlAttribute
    0.66
     تضيفلها
    0.66
    Activations Density 0.785%

    No Known Activations