© 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. 0-RES-MATRYOSHKA-DC
    7. 11578
    Prev
    Next
    INDEX
    Explanations

    references and mentions of transportation devices, specifically those related to electric rail systems and overhead line equipment

    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
     Normdatei
    -0.71
    ModelSerializer
    -0.69
     CreateTagHelper
    -0.60
    >[]
    -0.57
    },{
    -0.57
    tamol
    -0.57
     accept
    -0.56
    HasForeignKey
    -0.56
    tvguidetime
    -0.56
     فريبيس
    -0.55
    POSITIVE LOGITS
     commute
    3.23
     commuting
    2.06
     Commute
    1.98
     commuters
    1.44
     commuter
    1.40
    commut
    1.05
    通勤
    1.02
     comm
    0.71
    muting
    0.56
    muted
    0.54
    Activations Density 0.002%

    No Known Activations