© 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. 96529
    Prev
    Next
    INDEX
    Explanations

    Change/position

    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
    出版年
    -0.54
    ❋
    -0.54
    ERIES
    -0.53
    awtextra
    -0.50
    xty
    -0.49
     initComponents
    -0.49
    TestingModule
    -0.49
    auces
    -0.48
    ILogger
    -0.47
     videre
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.69
    Portale
    0.63
    StructEnd
    0.61
    bootstrapcdn
    0.59
     typelib
    0.55
    TagMode
    0.54
    stdc
    0.51
     Harrell
    0.50
     Harlem
    0.49
    RenderAtEndOf
    0.49
    Activations Density 0.002%

    No Known Activations