© 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. 6112
    Prev
    Next
    INDEX
    Explanations

    distinctions or features related to specific classifications or categories within 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
    ]--;
    -0.48
     tatouage
    -0.46
     الدولى
    -0.44
    ❸
    -0.43
    нъ
    -0.42
    vábbi
    -0.41
    かれています
    -0.40
     komende
    -0.40
    warted
    -0.39
     competing
    -0.39
    POSITIVE LOGITS
     noqa
    0.85
    Vidite
    0.80
    ymce
    0.73
    SuppressMessage
    0.72
    ContentAsync
    0.69
    Décès
    0.68
    saraba
    0.68
     forState
    0.68
    ngdoc
    0.68
     mxArray
    0.66
    Activations Density 4.739%

    No Known Activations