© 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. 0-RES-MATRYOSHKA-DC
    7. 12149
    Prev
    Next
    INDEX
    Explanations

    references to specific professionals and titles, particularly individuals involved in legal or technical roles

    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
    Lähteet
    -0.72
    principalColumn
    -0.63
     officials
    -0.59
     isInitialized
    -0.57
     representatives
    -0.56
     Minute
    -0.54
     Audiodateien
    -0.54
    Viitteet
    -0.54
     saites
    -0.52
     initComponents
    -0.52
    POSITIVE LOGITS
     Judges
    1.06
     Leaders
    0.96
     Candidates
    0.92
     Authors
    0.91
     Scientists
    0.91
     Founders
    0.88
     Engineers
    0.87
     Officers
    0.85
     Readers
    0.85
     Voters
    0.84
    Activations Density 0.189%

    No Known Activations