© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14245
    Prev
    Next
    INDEX
    Explanations

    recognition of specific patterns or structures in complex biological or chemical data

    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
     recognise
    -1.13
     recognize
    -1.10
     recognised
    -1.02
     recognizes
    -0.97
     recognises
    -0.96
     recognized
    -0.91
     reconhe
    -0.76
     Recognize
    -0.75
    recogn
    -0.74
    recognized
    -0.73
    POSITIVE LOGITS
     recognition
    1.28
    recognition
    1.20
     Recognition
    1.16
    Recognition
    1.00
    SceneManagement
    0.84
    脚注の使い方
    0.75
     acknowledgment
    0.69
    RenderAtEndOf
    0.69
     attent
    0.65
     consideration
    0.63
    Activations Density 0.002%

    No Known Activations