© 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. 14465
    Prev
    Next
    INDEX
    Explanations

    snippets of code involving creation of new objects or instances

    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
    getDoctrine
    -0.54
    posedge
    -0.52
    uture
    -0.51
     future
    -0.50
    utenant
    -0.50
    ientôt
    -0.49
    endOf
    -0.49
     recently
    -0.48
    getStatusCode
    -0.48
     date
    -0.48
    POSITIVE LOGITS
    new
    1.44
    Personensuche
    0.87
     متعلقه
    0.81
    MigrationBuilder
    0.68
     AssemblyCulture
    0.68
    Tikang
    0.66
     ujednoznacz
    0.64
    PageFactory
    0.64
     Refle
    0.63
    NEW
    0.63
    Activations Density 0.010%

    No Known Activations