© 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. 2-RES-MATRYOSHKA-DC
    7. 4554
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name, particularly Elizabeth

    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
     she
    -0.55
    her
    -0.53
    цима
    -0.49
    inigte
    -0.49
    $__
    -0.48
     Schroeder
    -0.48
    üten
    -0.47
    cler
    -0.47
    Denny
    -0.47
     AP
    -0.46
    POSITIVE LOGITS
     Elizabeth
    3.33
    Elizabeth
    3.14
     ELIZABETH
    2.83
     elizabeth
    2.41
     Elisabeth
    2.05
    elizabeth
    1.97
    IZABETH
    1.83
    Elisabeth
    1.67
     Eliz
    1.60
     Elizabethan
    1.50
    Activations Density 0.002%

    No Known Activations