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. 20-CLT-HP
    4. 74436
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <eos>
    -0.52
    <bos>
    -0.52
     &
    -0.47
    -
    -0.46
     -
    -0.46
     or
    -0.44
     and
    -0.43
    /
    -0.41
    ↵↵
    -0.41
    -/
    -0.40
    POSITIVE LOGITS
     myſelf
    1.54
     Efq
    1.54
     themſelves
    1.47
     itſelf
    1.46
     himſelf
    1.46
     Shakspeare
    1.42
     ſeveral
    1.41
     becauſe
    1.41
     Jefus
    1.40
     Monfieur
    1.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.