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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93745
    Prev
    Next
    INDEX
    Explanations

    peace

    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
    peace
    -0.90
    ness
    -0.64
    Peace
    -0.63
    чик
    -0.59
     Pace
    -0.57
    atoires
    -0.57
     Councils
    -0.57
     PyTuple
    -0.55
     betweenstory
    -0.54
    깥
    -0.54
    POSITIVE LOGITS
     ویکی‌پدیای
    0.59
     للمعارف
    0.58
    scrapy
    0.58
    <bos>
    0.57
    ReusableCell
    0.54
    StreetMap
    0.50
    modb
    0.48
    OptionsMenu
    0.48
    TagMode
    0.48
    ualmente
    0.48
    Activations Density 1.662%

    No Known Activations