© 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. 2-RES-MATRYOSHKA-DC
    7. 5496
    Prev
    Next
    INDEX
    Explanations

    code snippets related to configuring or executing network requests and handling multipart/form-data content

    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
     desertion
    -0.51
     terrorismo
    -0.43
     Jorge
    -0.42
    cpf
    -0.41
    use
    -0.40
    makta
    -0.40
    does
    -0.40
    .
    -0.39
    റ
    -0.39
     mạng
    -0.39
    POSITIVE LOGITS
    DockStyle
    1.02
     AssemblyTitle
    1.00
    WebServlet
    0.96
    ]")]
    0.96
     '\\;'
    0.96
     Италијани
    0.94
    IsContent
    0.89
    ftagPool
    0.88
     propOrder
    0.87
    AndEndTag
    0.84
    Activations Density 1.346%

    No Known Activations