© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11356
    Prev
    Next
    INDEX
    Explanations

    archive

    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
     Archive
    -1.23
    Archive
    -1.09
     archive
    -1.09
    archive
    -1.08
     Archives
    -0.85
     archives
    -0.83
     archival
    -0.80
    ARCHIVE
    -0.72
    Archives
    -0.72
    archives
    -0.72
    POSITIVE LOGITS
    ItemBackground
    0.56
    ?}",
    0.56
    queryInterface
    0.55
    IsContent
    0.54
    createCell
    0.50
    ButtonModule
    0.49
    DataAnnotations
    0.49
     createContext
    0.49
     Normdatei
    0.48
    unknownFields
    0.47
    Activations Density 0.018%

    No Known Activations