© 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. 1-CLT-HP
    7. 13429
    Prev
    Next
    INDEX
    Explanations

    replacement

    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
     replaced
    -0.98
     replace
    -0.94
    replace
    -0.90
    replaced
    -0.89
     replacement
    -0.89
     replacements
    -0.88
     Replacing
    -0.85
     replacing
    -0.84
     replaces
    -0.84
     Replace
    -0.83
    POSITIVE LOGITS
    DockStyle
    0.62
     pillows
    0.60
    BeginContext
    0.54
     محفوظة
    0.50
    agrave
    0.49
    SourceChecksum
    0.49
     bowls
    0.49
     pillow
    0.49
     cushions
    0.48
     mattresses
    0.47
    Activations Density 0.089%

    No Known Activations