© 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. 3335
    Prev
    Next
    INDEX
    Explanations

    references to sports statistics and player performances

    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
    +#+
    -0.69
     Baillargeon
    -0.61
    ValueGeneration
    -0.59
    tagHelperRunner
    -0.58
    AspNetCore
    -0.56
     &___
    -0.56
    minyak
    -0.55
     Duitse
    -0.53
     happiest
    -0.52
     Rumuni
    -0.51
    POSITIVE LOGITS
    windowFixed
    0.66
    ImageContext
    0.60
    <bos>
    0.59
    stateProvider
    0.59
    клопе
    0.57
    Identyfik
    0.57
    EndContext
    0.56
    endom
    0.56
    SupportActionBar
    0.56
     HttpNotFound
    0.55
    Activations Density 1.617%

    No Known Activations