© 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. 43733
    Prev
    Next
    INDEX
    Explanations

    publicly

    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
     يتيمه
    -0.91
     <=",
    -0.75
     élevées
    -0.73
    queryInterface
    -0.71
    AddTagHelper
    -0.70
     dévelo
    -0.67
    WriteBarrier
    -0.67
    VIAF
    -0.64
     '\\;'
    -0.64
     JpaRepository
    -0.63
    POSITIVE LOGITS
     of
    0.63
    vy
    0.53
     the
    0.50
    隔
    0.49
     it
    0.49
     committed
    0.49
     intended
    0.48
     present
    0.47
    хай
    0.47
     you
    0.46
    Activations Density 0.119%

    No Known Activations