© 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. 0-CLT-HP
    7. 92969
    Prev
    Next
    INDEX
    Explanations

    staging

    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
     Scheduling
    -0.50
    gall
    -0.49
     staging
    -0.47
     Coupling
    -0.47
     Grosvenor
    -0.47
    programming
    -0.47
     Coding
    -0.46
     Routing
    -0.46
    staging
    -0.45
     Deleting
    -0.45
    POSITIVE LOGITS
    المكان
    0.86
    webElementXpaths
    0.77
     onCancelled
    0.71
    $.
    0.70
    tvguidetime
    0.70
    ValueGeneration
    0.70
    Попис
    0.70
    HandlerContext
    0.69
    ^(@)
    0.68
     houſe
    0.66
    Activations Density 0.056%

    No Known Activations