© 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. 5-CLT-HP
    7. 878
    Prev
    Next
    INDEX
    Explanations

    strates

    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
    一种
    -0.69
     ostavi
    -0.63
     adaptations
    -0.62
     تضيفلها
    -0.61
    这种
    -0.61
    twimg
    -0.60
     Style
    -0.59
    MessageOf
    -0.58
    了一种
    -0.58
    Style
    -0.58
    POSITIVE LOGITS
    sendRedirect
    0.49
     vời
    0.46
     angesch
    0.46
     eyeball
    0.45
    pośred
    0.44
     lolita
    0.44
    untura
    0.44
    ServletException
    0.43
    ressum
    0.43
    URIComponent
    0.43
    Activations Density 0.005%

    No Known Activations