Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14507
    Prev
    Next
    INDEX
    Explanations

    mentions of the game of chess or related terms

    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
     JADX
    -0.69
    PathVariable
    -0.65
     Roskov
    -0.62
    PathParam
    -0.58
     لينك
    -0.55
     betweenstory
    -0.54
     Sparks
    -0.53
     Hannes
    -0.52
     Balboa
    -0.52
    banken
    -0.52
    POSITIVE LOGITS
     Chess
    3.16
     chess
    2.92
    Chess
    2.67
    chess
    2.22
     ajedrez
    1.47
     Schach
    1.34
     xadrez
    1.21
     checker
    1.16
    棋
    1.16
     checkers
    1.05
    Activations Density 0.003%

    No Known Activations