© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 655
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS snippets

    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
    expandindo
    -0.81
     يتيمه
    -0.77
    UpInside
    -0.63
     ComVisible
    -0.52
    cookieParser
    -0.51
     članak
    -0.50
    testify
    -0.48
     ویکی‌پدی
    -0.48
    tagHelperRunner
    -0.47
    DOCTYPE
    -0.47
    POSITIVE LOGITS
     Planners
    0.60
    plan
    0.59
    #+#
    0.59
    Plan
    0.56
     Plan
    0.56
    velle
    0.55
    faits
    0.55
    ollectionView
    0.55
    :][
    0.54
    __(/*!
    0.54
    Activations Density 0.002%

    No Known Activations