© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15719
    Prev
    Next
    INDEX
    Explanations

    references to a specific molecular size measurement associated with transition metals

    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
     propOrder
    -0.90
     defaultstate
    -0.83
     ligiloj
    -0.72
     Wallflower
    -0.61
     dévou
    -0.60
    éndolo
    -0.59
    FTFY
    -0.57
     "..\..\
    -0.57
     financeira
    -0.57
    recrow
    -0.57
    POSITIVE LOGITS
     diam
    3.50
    diam
    3.20
    Diam
    2.52
     Diam
    2.25
     DIAM
    1.54
    DIAM
    1.16
     diameter
    1.11
    diameter
    0.95
     Diameter
    0.95
     diameters
    0.84
    Activations Density 0.002%

    No Known Activations