Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44441
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     log
    -0.62
    ical
    -0.60
    ki
    -0.59
     ProtoMessage
    -0.56
    ines
    -0.52
     Jacobs
    -0.49
    Ệ
    -0.47
     match
    -0.45
     ki
    -0.45
      
    -0.45
    POSITIVE LOGITS
     Houſe
    0.94
     itſelf
    0.91
     houſe
    0.89
     Reſ
    0.89
     Diſ
    0.87
     ſever
    0.85
     themſelves
    0.85
     Eſ
    0.84
     pleaſure
    0.84
    ſelf
    0.84
    Activations Density 0.050%

    No Known Activations