© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    references to baseball players, teams, and related game events

    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
     préfé
    -0.82
    longValue
    -0.82
     Joko
    -0.78
     Lyt
    -0.78
     Schuyler
    -0.77
     getResource
    -0.75
    ruptedException
    -0.74
    MessageOf
    -0.74
     Bouch
    -0.73
    estat
    -0.71
    POSITIVE LOGITS
     Tow
    0.86
     tow
    0.82
    Tow
    0.73
    ForRow
    0.73
     Swift
    0.72
    Swift
    0.69
    LabelTagHelper
    0.68
     Ukrainian
    0.67
    rungsseite
    0.67
    urnum
    0.67
    Activations Density 2.044%

    No Known Activations