© 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. 11174
    Prev
    Next
    INDEX
    Explanations

    references to the name and concept of King Kong

    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
    SqlClient
    -0.57
     Affaires
    -0.56
    SourceChecksum
    -0.56
    ItemBackground
    -0.54
     diputado
    -0.54
    CPtr
    -0.54
     quæ
    -0.53
     MNRAS
    -0.52
     بيها
    -0.52
     fédé
    -0.52
    POSITIVE LOGITS
    kong
    2.69
     Kong
    2.09
    Kong
    1.95
     kong
    1.73
     KONG
    1.37
    yntaxException
    0.67
    hysema
    0.59
    },{
    0.58
    Enllaces
    0.57
    콩
    0.55
    Activations Density 0.001%

    No Known Activations