© 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. 4-CLT-HP
    7. 2544
    Prev
    Next
    INDEX
    Explanations

    those

    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
     pères
    -0.70
     prêtres
    -0.69
     maîtres
    -0.63
    aarrggbb
    -0.63
     chrétiens
    -0.60
     '{@
    -0.60
    ",&
    -0.60
     Grecs
    -0.59
    ="@+
    -0.57
     /\.(
    -0.57
    POSITIVE LOGITS
     failures
    0.58
    ,
    0.50
     fail
    0.50
     članak
    0.50
     Weltkrieg
    0.48
    pdata
    0.47
    MemoryWarning
    0.46
    AccessorTable
    0.45
    AsUp
    0.43
     diets
    0.43
    Activations Density 0.005%

    No Known Activations