© 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. 73216
    Prev
    Next
    INDEX
    Explanations

    Colonies and colonization

    np_max-act-logits · 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
    Colonial
    -1.06
     Colonial
    -1.00
    Colon
    -0.98
    Colony
    -0.97
     Colony
    -0.96
    colonial
    -0.96
     COLON
    -0.93
     Colon
    -0.93
    COLON
    -0.93
    colony
    -0.91
    POSITIVE LOGITS
     SOD
    0.49
     Trat
    0.45
     FOS
    0.44
    ctype
    0.44
    Set
    0.44
     }}{\
    0.44
     AO
    0.42
     Finnish
    0.42
    cco
    0.42
     EO
    0.42
    Activations Density 0.001%

    No Known Activations