© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    references to the name "King," likely indicating that it detects mentions of "King" or related royal or notable figures named King

    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
     Royals
    -0.82
     Duchess
    -0.81
     Empire
    -0.78
     ROYAL
    -0.77
     Royal
    -0.76
    Royal
    -0.74
     duchess
    -0.72
    Empire
    -0.71
     princely
    -0.71
     princes
    -0.71
    POSITIVE LOGITS
     King
    2.56
    King
    2.41
     KING
    2.16
     king
    2.03
    KING
    1.53
    king
    1.50
     Kings
    1.27
    キング
    1.18
     kings
    1.07
    kings
    1.04
    Activations Density 0.009%

    No Known Activations