© 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. 14010
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or recipients

    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
     winning
    -0.67
     winners
    -0.66
     winner
    -0.65
    winning
    -0.62
     Winning
    -0.58
    winners
    -0.56
    Winning
    -0.55
    Winner
    -0.53
     Winner
    -0.53
     Ouverture
    -0.52
    POSITIVE LOGITS
     recipient
    2.30
     recipients
    2.20
    recipient
    2.17
     Recipient
    1.96
     Recipients
    1.93
    Recipient
    1.90
    Recipients
    1.70
    recipients
    1.62
     RECIP
    1.48
    RECIP
    1.30
    Activations Density 0.002%

    No Known Activations