© 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. 0-CLT-HP
    7. 45610
    Prev
    Next
    INDEX
    Explanations

    pare

    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
    pare
    -1.15
     lighten
    -0.67
     pare
    -0.59
    Pare
    -0.57
    docx
    -0.55
    ValueGeneration
    -0.54
    بوابة
    -0.52
    taste
    -0.50
    VolleyError
    -0.50
    ագրություններ
    -0.50
    POSITIVE LOGITS
     ویکی‌پدیای
    0.69
    ثيق
    0.58
    )*/
    0.58
    Према
    0.57
    лтамалар
    0.54
     ویکی‌پدیا
    0.54
    Sucesor
    0.54
    مقدمه
    0.53
     referenties
    0.52
    expandindo
    0.51
    Activations Density 1.746%

    No Known Activations