© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13245
    Prev
    Next
    INDEX
    Explanations

    activities related to mechanical movement or operation

    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
     estekak
    -0.59
     okuyayım
    -0.59
     directors
    -0.58
    ennium
    -0.56
    httpMethod
    -0.56
     Kommune
    -0.54
    knife
    -0.54
     Directors
    -0.54
     HttpNotFound
    -0.53
     operation
    -0.52
    POSITIVE LOGITS
     oper
    2.86
     Oper
    1.99
    Oper
    1.67
    oper
    1.26
     OPER
    1.23
     opér
    1.03
     operas
    0.81
    operable
    0.79
     opera
    0.75
    OPER
    0.70
    Activations Density 0.004%

    No Known Activations