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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 9581
    Prev
    Next
    INDEX
    Explanations

    references to chess tournaments and competitions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WHM
    -0.52
    argout
    -0.52
    Corollary
    -0.50
     relie
    -0.50
     wretch
    -0.49
    lső
    -0.49
    jeans
    -0.48
    providing
    -0.48
    انتهای
    -0.48
    TAWA
    -0.47
    POSITIVE LOGITS
     chess
    1.30
     Chess
    1.20
    chess
    1.05
    Chess
    1.02
     ajedrez
    1.02
    ########.
    0.77
    TacToe
    0.77
    棋
    0.76
    TagMode
    0.73
    RegressionTest
    0.72
    Activations Density 0.012%

    No Known Activations