© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71627
    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
     Manufacturing
    -0.73
    Manufacturing
    -0.69
     MANUFACTURING
    -0.63
    Indust
    -0.58
     MANUFACT
    -0.55
     manufacturing
    -0.54
    manufacturing
    -0.52
     Manufac
    -0.51
     comércio
    -0.51
     industrial
    -0.51
    POSITIVE LOGITS
    moiselle
    0.67
     Taktlose
    0.57
     الحره
    0.56
     муніципалі
    0.56
     Dies
    0.55
    انجليز
    0.55
    ην
    0.52
     picker
    0.52
    Життєпис
    0.52
     piece
    0.52
    Activations Density 0.000%

    No Known Activations