© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6367
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly experts or professionals in the context of legal or scientific discussions

    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
     Saint
    -0.63
    Saint
    -0.59
     Lawyer
    -0.57
     engineer
    -0.56
     Sirs
    -0.54
     lawyer
    -0.53
     Engineer
    -0.53
     attorney
    -0.53
    bravo
    -0.51
    gure
    -0.50
    POSITIVE LOGITS
     Dr
    2.66
    Dr
    2.55
     dr
    1.80
    dr
    1.66
     Drs
    1.46
     DR
    1.18
    DR
    1.13
     دکتر
    1.08
     docteur
    1.06
    دکتر
    1.03
    Activations Density 0.009%

    No Known Activations