© 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. 14324
    Prev
    Next
    INDEX
    Explanations

    a

    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
    DockStyle
    -0.80
    
    -0.68
    RegressionTest
    -0.68
     '\\;'
    -0.66
     يتيمه
    -0.65
    NameInMap
    -0.60
    expandindo
    -0.60
    原始内容存档
    -0.60
    +#+#
    -0.57
    roffene
    -0.57
    POSITIVE LOGITS
     lot
    0.56
    AddTagHelper
    0.56
     few
    0.54
     list
    0.51
     book
    0.50
     document
    0.49
    __':
    0.48
     provato
    0.48
     new
    0.47
     bunch
    0.47
    Activations Density 0.015%

    No Known Activations