© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15362
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tread" or related forms referring to the component of a tire

    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
    Westfalen
    -0.63
    writeFieldEnd
    -0.62
    ذي
    -0.59
     _{\
    -0.57
     Popp
    -0.56
    áni
    -0.54
     Sorensen
    -0.54
    лакти
    -0.53
    ClientRect
    -0.53
     betweenstory
    -0.53
    POSITIVE LOGITS
     tread
    4.03
     Tread
    2.97
     treads
    2.45
     treadmill
    1.84
     tred
    1.26
     trod
    1.19
    apunov
    0.73
    migrationBuilder
    0.72
     tramp
    0.67
    MigrationBuilder
    0.66
    Activations Density 0.001%

    No Known Activations