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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12747
    Prev
    Next
    INDEX
    Explanations

    examined

    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
     ſever
    -1.02
     myſelf
    -0.98
     Jefus
    -0.97
     pleaſure
    -0.96
     Efq
    -0.93
     fevere
    -0.93
     Monfieur
    -0.91
     uſ
    -0.91
     Majefty
    -0.85
     themſelves
    -0.84
    POSITIVE LOGITS
     “
    0.85
     ‘
    0.82
     ...
    0.79
     '
    0.76
    ...
    0.73
     "
    0.73
    ”,
    0.70
    ”
    0.69
     …
    0.69
     
    0.67
    Activations Density 1.042%

    No Known Activations