© 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. 2-RES-MATRYOSHKA-DC
    7. 5549
    Prev
    Next
    INDEX
    Explanations

    references to molecules, compounds, or tools that are sensitive or specific to certain biological targets or receptors

    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
    存于互联网档案馆
    -0.72
     propOrder
    -0.60
    ństw
    -0.58
    UrlEncoded
    -0.57
     numberOfRows
    -0.57
    dataclass
    -0.57
    thaw
    -0.56
     karar
    -0.56
     &'
    -0.55
    ète
    -0.54
    POSITIVE LOGITS
     selective
    2.91
    Selective
    2.75
    selective
    2.75
     Selective
    2.70
     selectively
    2.45
     selectivity
    2.02
     sele
    1.24
     Sele
    1.18
    sele
    1.16
    Sele
    0.99
    Activations Density 0.004%

    No Known Activations