© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    references to medical signs or indicators

    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
     signature
    -0.79
     onOptions
    -0.75
     signatures
    -0.66
    sign
    -0.66
     AssemblyCulture
    -0.65
     signed
    -0.61
    proven
    -0.60
     signing
    -0.59
    signature
    -0.59
    Sign
    -0.59
    POSITIVE LOGITS
     signs
    2.31
    Signs
    2.05
     Signs
    1.98
     SIGNS
    1.73
    signs
    1.57
     signes
    1.52
     sinais
    1.25
     signos
    1.22
     segni
    0.96
     признаки
    0.88
    Activations Density 0.004%

    No Known Activations