© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 444
    Prev
    Next
    INDEX
    Explanations

    information related to professional roles and credentials

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ciertos
    -0.46
     psicológico
    -0.40
     žád
    -0.39
     loses
    -0.39
     bestemt
    -0.38
     minimal
    -0.38
     sní
    -0.38
     žá
    -0.38
     vissa
    -0.37
     podmín
    -0.37
    POSITIVE LOGITS
     assistant
    0.72
     AssemblyCompany
    0.72
     lecturer
    0.68
     educator
    0.68
     consultant
    0.66
     Efq
    0.66
     entrepreneur
    0.65
     specialising
    0.65
     freelance
    0.64
     analyst
    0.63
    Activations Density 2.836%

    No Known Activations