© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2873
    Prev
    Next
    INDEX
    Explanations

    business/news articles

    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
     task
    -0.57
    task
    -0.55
     Assist
    -0.51
    culoskeletal
    -0.51
    Task
    -0.50
    Népesség
    -0.49
    ERVIS
    -0.49
     tasked
    -0.49
     Supervis
    -0.49
     Tasks
    -0.48
    POSITIVE LOGITS
    tinyos
    0.66
    MessageOf
    0.63
     oprot
    0.61
    ValueStyle
    0.59
     ProtoMessage
    0.57
    جغرافيا
    0.54
     RequestMethod
    0.52
     Chwiliwch
    0.51
    ########.
    0.51
    ViewImports
    0.51
    Activations Density 0.000%

    No Known Activations