© 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. 4-CLT-HP
    7. 2952
    Prev
    Next
    INDEX
    Explanations

    post

    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
    ൃ
    -0.50
     Meksiku
    -0.46
    Cursors
    -0.44
    CURS
    -0.44
    OBJ
    -0.43
    MigrationBuilder
    -0.43
     eikä
    -0.43
    inst
    -0.42
    class
    -0.42
    الإ
    -0.42
    POSITIVE LOGITS
    Tikang
    0.81
     Paglinawan
    0.74
    BeginContext
    0.72
     summarize
    0.68
     summaries
    0.65
    脚注の使い方
    0.64
     summarized
    0.62
     summarizes
    0.62
     שוליים
    0.62
    InstanceState
    0.58
    Activations Density 0.001%

    No Known Activations