© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7658
    Prev
    Next
    INDEX
    Explanations

    lines of code involving object encoding and decoding, particularly those related to class method calls and object initialization

    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
    Negative Logits
    WriteTagHelper
    -1.00
    principalColumn
    -0.77
    تقاوى
    -0.76
    StoryboardSegue
    -0.70
     newBuilder
    -0.70
     JAXBElement
    -0.69
    oneofs
    -0.68
    Koordinaten
    -0.67
    RectangleBorder
    -0.65
    twimg
    -0.63
    POSITIVE LOGITS
     kasarigan
    0.70
    ########.
    0.68
    __":
    0.60
    "}}>
    0.60
    AxisAlignment
    0.58
    ༻
    0.57
    gapi
    0.56
    __':
    0.53
    >{@
    0.53
    로드
    0.53
    Activations Density 0.352%

    No Known Activations