© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14037
    Prev
    Next
    INDEX
    Explanations

    references to noble titles and noble rank indicators

    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
    PRNewswire
    -0.75
    fjspx
    -0.66
    Personensuche
    -0.57
    Datuak
    -0.57
    SpringRunner
    -0.55
    üte
    -0.54
     OFDb
    -0.54
    mainAxisSize
    -0.54
    Nonnull
    -0.53
    ')):
    -0.53
    POSITIVE LOGITS
     Baron
    3.67
    Baron
    2.94
     baron
    2.38
    baron
    1.64
     Baroness
    1.29
     barons
    1.15
     Barron
    1.07
     Viscount
    0.89
     Freih
    0.73
     Marquis
    0.63
    Activations Density 0.001%

    No Known Activations