© 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. 6022
    Prev
    Next
    INDEX
    Explanations

    references to specific vehicle components, primarily focusing on wheels and tires

    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
    XmlAccessorType
    -0.61
    "])
    -0.55
    sina
    -0.54
    createNewFile
    -0.54
    Története
    -0.54
    GeneratedMessage
    -0.53
     سكانية
    -0.53
     nakalista
    -0.53
    outSlope
    -0.52
    ipelago
    -0.52
    POSITIVE LOGITS
     wheel
    3.78
     Wheel
    3.47
    wheel
    3.39
    Wheel
    3.25
     WHEEL
    3.20
     wheels
    3.02
     Wheels
    2.72
    wheels
    2.67
    WHEEL
    2.64
    Wheels
    2.28
    Activations Density 0.010%

    No Known Activations