© 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. 1-RES-MATRYOSHKA-DC
    7. 769
    Prev
    Next
    INDEX
    Explanations

    references to request handling or related HTTP request processes

    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
    want
    -0.88
     want
    -0.86
     wanted
    -0.85
    wanted
    -0.75
     Want
    -0.73
    Want
    -0.70
     WANT
    -0.69
    WANT
    -0.68
     wanna
    -0.65
    intended
    -0.65
    POSITIVE LOGITS
     request
    4.19
    request
    3.92
     Request
    3.88
    Request
    3.61
     requests
    3.56
     Requests
    3.33
     REQUEST
    3.30
    REQUEST
    3.00
    requests
    2.98
    Requests
    2.92
    Activations Density 0.182%

    No Known Activations