© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 942
    Prev
    Next
    INDEX
    Explanations

    references to measurements and quantities of chemical substances

    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
    WebElementEntity
    -0.57
     sim
    -0.52
    芒
    -0.51
    essen
    -0.48
     Mante
    -0.47
     hours
    -0.46
     proto
    -0.46
     Altman
    -0.45
     fire
    -0.45
    grim
    -0.45
    POSITIVE LOGITS
     mL
    2.67
    mL
    2.42
     ml
    2.22
    ml
    2.13
     mM
    1.74
     mg
    1.55
    ML
    1.54
     ML
    1.52
    mM
    1.45
    mg
    1.35
    Activations Density 0.224%

    No Known Activations