© 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. 3203
    Prev
    Next
    INDEX
    Explanations

    listing multiple reasons/elements

    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
     للاسماء
    -0.72
    protoimpl
    -0.71
     harder
    -0.67
    better
    -0.58
     tougher
    -0.58
    ValueStyle
    -0.57
     typelib
    -0.56
     stiffer
    -0.56
    LayoutStyle
    -0.56
    PerformLayout
    -0.56
    POSITIVE LOGITS
     then
    0.65
    cellona
    0.57
    PutMapping
    0.53
     Then
    0.51
    Then
    0.50
    ówczas
    0.48
    而
    0.48
    couvrez
    0.48
     out
    0.47
    sság
    0.47
    Activations Density 0.002%

    No Known Activations