© 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. 120
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    StoryboardSegue
    -1.05
     CreateTagHelper
    -0.94
     '\\;'
    -0.92
    RenderAtEndOf
    -0.81
     ModelExpression
    -0.80
     متعلقه
    -0.75
     Biôgrafia
    -0.71
    reportWebVitals
    -0.69
    BagConstraints
    -0.69
    :✨
    -0.69
    POSITIVE LOGITS
     tensione
    0.46
     makes
    0.44
     presence
    0.40
     naudoti
    0.40
    ge
    0.37
     ch
    0.37
     terlalu
    0.36
     the
    0.36
    erman
    0.36
     али
    0.36
    Activations Density 0.011%

    No Known Activations