© 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. 1-CLT-HP
    7. 8848
    Prev
    Next
    INDEX
    Explanations

    street

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
     street
    -0.84
     Street
    -0.77
     STREET
    -0.76
    Street
    -0.71
    STREET
    -0.62
    street
    -0.57
     straat
    -0.50
     Streets
    -0.48
     streets
    -0.48
     bicchiere
    -0.48
    POSITIVE LOGITS
    work
    0.63
    rage
    0.62
    life
    0.61
    works
    0.58
    voice
    0.54
    mates
    0.54
    fycat
    0.54
    craft
    0.53
    corner
    0.52
    fight
    0.51
    Activations Density 0.006%

    No Known Activations