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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74420
    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
     Efq
    -0.66
     Cæsar
    -0.63
     Monfieur
    -0.60
     pleaſure
    -0.59
     Majefty
    -0.56
     houſe
    -0.53
     myſelf
    -0.52
     raiſ
    -0.52
     alternation
    -0.50
     purpoſe
    -0.50
    POSITIVE LOGITS
    "];
    
    0.71
    ":
    
    0.70
     Get
    0.70
     hiér
    0.68
     “
    0.68
    发表于
    0.68
    paravant
    0.68
    ':
    
    0.66
    ”“
    0.66
     fuite
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.