© 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. 96497
    Prev
    Next
    INDEX
    Explanations

    when

    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
    Билгалдахарш
    -0.86
     BorderSide
    -0.64
     himo
    -0.59
     oprot
    -0.56
    medriver
    -0.54
    StructEnd
    -0.52
     समीक्षक
    -0.50
    ագրություններ
    -0.50
    principalColumn
    -0.50
      (
    -0.49
    POSITIVE LOGITS
     Being
    0.72
     To
    0.71
     It
    0.70
     They
    0.70
     to
    0.69
     Is
    0.66
     Will
    0.65
     We
    0.62
     Was
    0.60
     And
    0.60
    Activations Density 0.017%

    No Known Activations