© 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. 12838
    Prev
    Next
    INDEX
    Explanations

    references to skilled or highly trained professionals

    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
     estekak
    -0.73
    neurial
    -0.70
     career
    -0.68
    RetentionPolicy
    -0.68
    Спољашње
    -0.66
    endpush
    -0.64
     CAREER
    -0.61
     careers
    -0.60
     المعيارى
    -0.60
    Career
    -0.59
    POSITIVE LOGITS
     skilled
    2.59
     Skilled
    2.38
    skilled
    1.95
     unskilled
    1.50
     skillful
    1.23
     skilful
    1.09
     skillfully
    0.83
     adept
    0.71
    Sk
    0.65
     масте
    0.63
    Activations Density 0.001%

    No Known Activations