© 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. 4-CLT-HP
    7. 2619
    Prev
    Next
    INDEX
    Explanations

    luggage

    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
     '\\;'
    -0.81
     utafitiHapana
    -0.76
    новниш
    -0.72
    الحياه
    -0.70
    expandindo
    -0.70
     AppColors
    -0.68
     sqlSession
    -0.67
     StatefulWidget
    -0.66
    Datuak
    -0.65
     houſe
    -0.65
    POSITIVE LOGITS
    <bos>
    0.71
     provision
    0.50
    줍
    0.46
    ğine
    0.45
     mis
    0.44
    ParallelGroup
    0.43
     limit
    0.43
     tip
    0.42
    ριθ
    0.42
     &___
    0.42
    Activations Density 0.015%

    No Known Activations