© 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. 4549
    Prev
    Next
    INDEX
    Explanations

    references to recombinant protein or gene technology

    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
    oredCriteria
    -0.63
    SN
    -0.52
    MFG
    -0.52
    yang
    -0.50
    ث
    -0.50
    מית
    -0.49
    chaus
    -0.48
    prilis
    -0.48
     schme
    -0.47
    weis
    -0.47
    POSITIVE LOGITS
     recombinant
    3.09
    binant
    2.81
     Recom
    1.93
    Recom
    1.76
    recom
    1.66
     recombination
    1.55
     recom
    1.43
     RECOM
    1.34
     transgenic
    0.79
    bination
    0.79
    Activations Density 0.002%

    No Known Activations