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. 20-CLT-HP
    4. 74113
    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
    RetentionPolicy
    -0.58
    OrBuilder
    -0.46
    #+#
    -0.45
     AssemblyTitle
    -0.44
    __':
    
    -0.44
    Number
    -0.43
     ulei
    -0.43
    nloa
    -0.42
     vérit
    -0.42
    [])
    
    -0.42
    POSITIVE LOGITS
    -
    0.59
    ThroughAttribute
    0.58
     незавершена
    0.57
    -<
    0.54
    ChildScrollView
    0.49
    crest
    0.49
    تقاوى
    0.47
     transfieras
    0.46
    ringing
    0.46
    ackerel
    0.45
    Activations Density 0.000%

    No Known Activations