© 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. 2-RES-MATRYOSHKA-DC
    7. 6064
    Prev
    Next
    INDEX
    Explanations

    references to molecular quantities or measurements

    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
    WindowConstants
    -0.75
     ſch
    -0.73
     ſta
    -0.72
     himſelf
    -0.70
     Matsumoto
    -0.68
     ſon
    -0.66
     ſtate
    -0.66
     ſen
    -0.65
     hysteresis
    -0.65
     cauſe
    -0.65
    POSITIVE LOGITS
    mol
    3.36
     mol
    3.02
     Mol
    2.56
    Mol
    2.47
     MOL
    2.09
    MOL
    2.09
     mmol
    1.57
     moles
    1.50
    moles
    1.41
    mmol
    1.40
    Activations Density 0.013%

    No Known Activations