© 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. 3802
    Prev
    Next
    INDEX
    Explanations

    references to specific junction points or crossings within geographic trail networks

    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
    tvguidetime
    -0.74
    putnik
    -0.71
    ReusableCell
    -0.66
     numberOfRows
    -0.63
    <_>
    -0.61
    aarrggbb
    -0.60
     invokingState
    -0.60
    crollView
    -0.59
    LabelTagHelper
    -0.59
    FromArgb
    -0.58
    POSITIVE LOGITS
     junction
    2.95
    junction
    2.80
     Junction
    2.64
    Junction
    2.53
     junctions
    2.47
     intersection
    2.44
     intersections
    1.99
     Intersection
    1.99
    Intersection
    1.95
    intersection
    1.90
    Activations Density 0.027%

    No Known Activations