© 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. 3850
    Prev
    Next
    INDEX
    Explanations

    references to a specific highway bridge in Kentucky and Indiana

    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
     Akira
    -0.64
    katapos
    -0.63
    ToScroll
    -0.62
    liffe
    -0.60
    AppRoutingModule
    -0.60
     McDermott
    -0.59
     Sorbonne
    -0.59
     Innsbruck
    -0.58
    kolwiek
    -0.58
     Agamemnon
    -0.57
    POSITIVE LOGITS
     Lewis
    3.63
    Lewis
    3.41
     lewis
    2.94
     LEWIS
    2.92
    lewis
    2.63
     Lew
    1.04
    Lew
    0.88
     Louis
    0.85
    Louis
    0.77
     Luis
    0.76
    Activations Density 0.002%

    No Known Activations