© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 939
    Prev
    Next
    INDEX
    Explanations

    especially

    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
    TagMode
    -0.77
    WebpackPlugin
    -0.69
     propOrder
    -0.68
     насељу
    -0.68
    onAttach
    -0.67
     oprot
    -0.67
    PMailer
    -0.67
    IUrlHelper
    -0.65
    enumi
    -0.63
    RenderAtEndOf
    -0.63
    POSITIVE LOGITS
    runOnUiThread
    0.54
    centralwidget
    0.52
     confusion
    0.51
    ]();
    0.51
     about
    0.50
     χρόν
    0.48
    iliation
    0.48
     physical
    0.48
    awtextra
    0.48
    AILABILITY
    0.46
    Activations Density 0.007%

    No Known Activations