© 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. 3-RES-MATRYOSHKA-DC
    7. 3433
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Roman" or "Rome."

    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
    Negative Logits
     anſ
    -0.88
     Efq
    -0.85
     Monfieur
    -0.82
     Anſ
    -0.81
    ThroughAttribute
    -0.80
     reaſon
    -0.79
    tinyos
    -0.76
     ſtand
    -0.76
     reafon
    -0.76
     poffe
    -0.75
    POSITIVE LOGITS
     Roman
    3.02
    Roman
    2.77
     ROMAN
    2.38
     roman
    2.33
    roman
    2.03
     Romans
    1.91
     Rome
    1.80
     Rom
    1.73
     romans
    1.67
     Romana
    1.63
    Activations Density 0.014%

    No Known Activations