© 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. 5252
    Prev
    Next
    INDEX
    Explanations

    references to measurements of distance or size

    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
    principalColumn
    -0.62
     ounce
    -0.61
     ExecuteAsync
    -0.60
    mmol
    -0.59
     Numerade
    -0.58
     ounces
    -0.58
     Roskov
    -0.57
    ChildIndex
    -0.56
    obiety
    -0.55
     onCreateView
    -0.55
    POSITIVE LOGITS
     meters
    1.08
     metres
    1.03
     meter
    0.89
     distance
    0.87
     metre
    0.84
     Meter
    0.81
    Meters
    0.81
     Meters
    0.79
    meters
    0.73
    metres
    0.70
    Activations Density 0.218%

    No Known Activations