© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    references to individuals holding leadership or authoritative positions

    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
    SerializeField
    -0.52
     cos
    -0.52
     lead
    -0.52
    ParallelGroup
    -0.51
    reveal
    -0.50
     Magnum
    -0.50
     Leads
    -0.49
     Cos
    -0.49
    TouchListener
    -0.48
     департа
    -0.47
    POSITIVE LOGITS
     leader
    2.94
     leaders
    2.88
     Leader
    2.75
     Leaders
    2.73
    Leaders
    2.70
    Leader
    2.66
    leader
    2.64
    leaders
    2.55
     LEADER
    2.41
     leadership
    2.30
    Activations Density 0.016%

    No Known Activations