© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10743
    Prev
    Next
    INDEX
    Explanations

    references to specific types of medicinal and biological compounds consistently associated with activity or substances used in biomedical contexts

    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
    GeneratedCode
    -0.58
    keit
    -0.50
    MessageInfo
    -0.47
     похо
    -0.47
    濱
    -0.45
     ke
    -0.45
     כל
    -0.42
     Loeb
    -0.42
    너
    -0.42
    fam
    -0.42
    POSITIVE LOGITS
    ativa
    2.84
    ativas
    2.69
    ativo
    2.56
    ativ
    2.52
    ativos
    2.30
    ativi
    2.05
    ATIVA
    1.98
    ativen
    1.75
    ATIVO
    1.66
    atif
    1.62
    Activations Density 0.007%

    No Known Activations