© 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. 1-RES-MATRYOSHKA-DC
    7. 839
    Prev
    Next
    INDEX
    Explanations

    references to roads, trails, highways, and related transportation infrastructure

    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
    IMPORTED
    -0.60
    AndEndTag
    -0.49
     reposo
    -0.47
     crystals
    -0.44
     crystal
    -0.43
    Pyx
    -0.42
    vats
    -0.41
    NullException
    -0.41
     inserire
    -0.41
     retainer
    -0.41
    POSITIVE LOGITS
     road
    3.66
     Road
    3.36
    Road
    3.27
    road
    3.19
     ROAD
    3.11
     roads
    3.05
    ROAD
    2.95
     highway
    2.83
     Roads
    2.73
     Highway
    2.64
    Activations Density 0.405%

    No Known Activations