© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15446
    Prev
    Next
    INDEX
    Explanations

    references to code snippets or highlighted formatting elements in the text

    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
    IVEREF
    -0.66
     Guru
    -0.65
    Guru
    -0.65
    guru
    -0.62
     Gur
    -0.62
    Gur
    -0.61
     StatefulWidget
    -0.59
    setObjectName
    -0.55
    gur
    -0.54
     gur
    -0.54
    POSITIVE LOGITS
    *************
    1.34
    **************
    1.02
    ************
    1.02
    **********
    0.98
    ***************
    0.96
    ***********
    0.91
    *********
    0.88
    *******
    0.77
    ********
    0.72
    dflare
    0.72
    Activations Density 0.056%

    No Known Activations