© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91111
    Prev
    Next
    INDEX
    Explanations

    existing

    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
    <bos>
    -0.65
     existing
    -0.64
     enfans
    -0.58
     remaining
    -0.57
     épaules
    -0.54
     oreilles
    -0.52
     Remaining
    -0.46
     setup
    -0.46
     cappuccio
    -0.45
     Existing
    -0.45
    POSITIVE LOGITS
     للمعارف
    1.01
     صوتيه
    1.01
     autorytatywna
    0.86
     propOrder
    0.83
    JspWriter
    0.79
     فريبيس
    0.79
    tagHelperRunner
    0.78
    setVerticalGroup
    0.76
     CreateTagHelper
    0.73
    ContentAlignment
    0.71
    Activations Density 0.009%

    No Known Activations