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. 0-CLT-HP
    4. 44444
    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
     to
    -1.27
     supérieurs
    -0.96
    出版年
    -0.90
    ThroughAttribute
    -0.85
     quelcon
    -0.85
    ⓧ
    -0.85
     виправивши
    -0.82
     extérieurs
    -0.82
     supérieures
    -0.81
     réglable
    -0.81
    POSITIVE LOGITS
     the
    0.79
     be
    0.64
     attend
    0.57
     have
    0.55
     distinguish
    0.53
     behave
    0.52
     undergo
    0.52
     hold
    0.52
     maintain
    0.49
     bring
    0.48
    Activations Density 0.122%

    No Known Activations