© 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. 1-CLT-HP
    7. 10880
    Prev
    Next
    INDEX
    Explanations

    names

    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
     οποίο
    -0.51
    skjaer
    -0.50
    s
    -0.49
    SqlClient
    -0.46
    wikkel
    -0.43
    +#+#
    -0.43
    sing
    -0.42
     οποία
    -0.42
    sider
    -0.41
    stylers
    -0.41
    POSITIVE LOGITS
    JspWriter
    0.75
    meat
    0.63
     iprot
    0.62
     архивлан
    0.61
     writeTo
    0.57
     surla
    0.57
    出版年
    0.57
    StoryboardSegue
    0.56
     يتيمه
    0.56
    itative
    0.56
    Activations Density 0.037%

    No Known Activations