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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 734
    Prev
    Next
    INDEX
    Explanations

    the term 'European' followed by an organization name

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.70
     يتيمه
    -0.66
     chileno
    -0.63
     glatt
    -0.60
     Egypt
    -0.57
    ConstraintMaker
    -0.57
     Paglinawan
    -0.56
     ddelweddau
    -0.56
     Mexiko
    -0.56
     Brasilien
    -0.56
    POSITIVE LOGITS
     European
    2.33
     Europe
    2.16
    European
    2.14
     EUROPEAN
    2.13
    Europe
    2.05
     european
    2.02
     Europeans
    2.00
     Europa
    1.99
     EUROPE
    1.98
     europea
    1.97
    Activations Density 0.245%

    No Known Activations