© 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. 0-CLT-HP
    7. 38334
    Prev
    Next
    INDEX
    Explanations

    include

    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
     includes
    -1.74
     include
    -1.68
     inclui
    -1.59
    include
    -1.57
     Includes
    -1.55
     Included
    -1.55
     incluem
    -1.53
     included
    -1.52
     incluye
    -1.52
    Included
    -1.52
    POSITIVE LOGITS
     a
    1.12
     the
    1.09
     an
    1.00
     some
    0.81
     what
    0.80
     this
    0.77
     another
    0.73
     their
    0.73
     many
    0.70
     something
    0.70
    Activations Density 0.074%

    No Known Activations