© 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. 43629
    Prev
    Next
    INDEX
    Explanations

    since

    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
     to
    -0.53
     siden
    -0.48
    oredCriteria
    -0.48
    s
    -0.48
     tri
    -0.46
     sfor
    -0.45
    另外
    -0.45
     dinas
    -0.44
     D
    -0.43
     mises
    -0.43
    POSITIVE LOGITS
     Efq
    0.86
     Whigs
    0.83
    ^(@)
    0.78
     Thessalon
    0.76
     abstrato
    0.73
     Magellan
    0.72
     ་་
    0.71
    mybatisplus
    0.70
     يتيمه
    0.70
    SceneManagement
    0.70
    Activations Density 0.590%

    No Known Activations