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. 20-CLT-HP
    4. 74181
    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
     positive
    -1.20
    positive
    -1.13
     Positive
    -1.12
    Positive
    -1.04
     POSITIVE
    -1.02
     positively
    -0.96
     positif
    -0.91
    POSITIVE
    -0.87
     positives
    -0.86
     positivas
    -0.86
    POSITIVE LOGITS
    Geographie
    0.49
    lename
    0.46
    ebra
    0.44
     للمعارف
    0.42
     religion
    0.41
     revanche
    0.39
     يتيمه
    0.38
     πάντα
    0.38
    рії
    0.36
    strtotime
    0.36
    Activations Density 0.003%

    No Known Activations