© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 3920
    Prev
    Next
    INDEX
    Explanations

    references to specific molecular pathways, genetic regulation, and biological mechanisms

    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
     Roskov
    -0.96
     >=",
    -0.94
    تقاوى
    -0.91
     AssemblyVersion
    -0.86
     tartalomajánló
    -0.84
    ArgsConstructor
    -0.80
    ]--;
    -0.79
     للمعارف
    -0.79
    GEBURTS
    -0.78
    Kjelder
    -0.77
    POSITIVE LOGITS
     arşivlendi
    0.43
    <eos>
    0.41
     rather
    0.40
     "../../../
    0.40
    企
    0.40
     predic
    0.39
    反
    0.38
    而
    0.38
    ẓ
    0.38
    }{*}{}
    0.38
    Activations Density 1.169%

    No Known Activations