© 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. 6927
    Prev
    Next
    INDEX
    Explanations

    references to visiting or traversing entities, particularly in code or document structures

    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
     travel
    -1.26
     Travel
    -1.18
    Travel
    -1.09
     TRAVEL
    -1.05
    travel
    -1.02
    TRAVEL
    -0.88
     traveling
    -0.79
     travelling
    -0.71
    Traveler
    -0.68
     access
    -0.68
    POSITIVE LOGITS
     visit
    3.03
    visit
    2.80
     visits
    2.75
     Visit
    2.70
     VISIT
    2.64
     Visits
    2.59
    Visit
    2.56
     visited
    2.53
    visits
    2.52
    VISIT
    2.42
    Activations Density 0.038%

    No Known Activations