© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90842
    Prev
    Next
    INDEX
    Explanations

    don

    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
    s
    -0.66
     is
    -0.59
     don
    -0.57
      
    -0.55
    ↵↵
    -0.52
     can
    -0.52
     N
    -0.50
     doesn
    -0.50
     (
    -0.49
     Of
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    AndEndTag
    0.93
    IntoConstraints
    0.88
    AccessorTable
    0.88
    存于互联网档案馆
    0.87
    ‟
    0.86
     Normdatei
    0.86
    RenderAtEndOf
    0.85
    InjectAttribute
    0.85
     مشين
    0.85
    Activations Density 0.365%

    No Known Activations