© 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. 937
    Prev
    Next
    INDEX
    Explanations

    th

    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
     înal
    -0.47
     diras
    -0.46
     coraggio
    -0.45
     déchir
    -0.44
    AutoScale
    -0.44
     dépla
    -0.44
     aéri
    -0.44
     žem
    -0.44
     lèvres
    -0.41
     necessárias
    -0.41
    POSITIVE LOGITS
     AssemblyVersion
    0.69
    HomeAsUpEnabled
    0.67
     Paglinawan
    0.66
     invokevirtual
    0.64
     архивлан
    0.63
    ArrowToggle
    0.62
    wpi
    0.61
     JpaRepository
    0.60
    ChildScrollView
    0.60
    IRUS
    0.59
    Activations Density 0.006%

    No Known Activations