© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95212
    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
    Autoritní
    -0.75
    \{\\
    -0.73
    
    -0.73
    GEBURTSDATUM
    -0.71
     déchir
    -0.71
     EconPapers
    -0.70
     الحره
    -0.69
     roligt
    -0.69
    WebElementEntity
    -0.68
     flesta
    -0.68
    POSITIVE LOGITS
     el
    0.54
     El
    0.51
    dens
    0.42
     invalid
    0.40
     when
    0.40
    demic
    0.40
    onomies
    0.40
    s
    0.39
     how
    0.39
    El
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.