© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23326
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     ROUTE
    -0.83
    "]];
    -0.82
     Routes
    -0.78
     Route
    -0.77
    ROUTE
    -0.76
    "]));
    -0.73
     ROUT
    -0.72
    mushroom
    -0.71
     Rout
    -0.69
    
    -0.69
    POSITIVE LOGITS
     navigation
    1.24
     Navigation
    1.13
     navig
    1.13
    avigation
    1.12
    Navigation
    1.11
    navigation
    1.02
     Navig
    1.02
     navigate
    1.02
    navigate
    1.01
    Navig
    0.95
    Activations Density 0.004%

    No Known Activations