© 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. 2-RES-MATRYOSHKA-DC
    7. 7310
    Prev
    Next
    INDEX
    Explanations

    lines of code involving script or command syntax elements such as pipes, dashes, options, and file paths

    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
    SceneManagement
    -0.54
     Gun
    -0.52
     prema
    -0.49
     yarar
    -0.49
    addGap
    -0.47
     nélkül
    -0.47
    ⓘ
    -0.47
    '>"
    -0.46
    findViewById
    -0.45
    bitField
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.87
     dAtA
    0.84
    AddTagHelper
    0.81
    PostInfinity
    0.69
    UrlResolution
    0.67
    BufferException
    0.65
    cury
    0.62
     CURIAM
    0.62
     CURLOPT
    0.61
    ('--
    0.60
    Activations Density 0.135%

    No Known Activations