© 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. 0-RES-MATRYOSHKA-DC
    7. 13046
    Prev
    Next
    INDEX
    Explanations

    references to a specific professional title, indicating a focus on addressing or identifying individuals holding that title

    oai_token-act-pair · gpt-4.1-nano
    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
     sir
    -1.53
     sire
    -0.96
    sir
    -0.94
     Majefty
    -0.90
     madam
    -0.86
     Efq
    -0.79
     houſe
    -0.75
     Houſe
    -0.75
     pleaſure
    -0.73
     monsieur
    -0.72
    POSITIVE LOGITS
     Sir
    1.63
    Sir
    1.24
     للاسماء
    0.65
    intios
    0.50
     g
    0.49
    hift
    0.49
    VersionUID
    0.49
     kasarigan
    0.47
     ;
    0.46
     Rev
    0.46
    Activations Density 0.001%

    No Known Activations