© 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. 14908
    Prev
    Next
    INDEX
    Explanations

    structural information about molecular conformations and assembly states

    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
    nodoc
    -0.65
    WriteBarrier
    -0.56
     uParam
    -0.51
    WithIOException
    -0.50
     kasarigan
    -0.49
    elernt
    -0.49
     assolu
    -0.48
     Kug
    -0.48
     Lipp
    -0.47
     Católica
    -0.46
    POSITIVE LOGITS
     monomer
    3.31
     monomers
    2.61
     lenker
    0.78
     dimer
    0.70
    webElement
    0.68
    expandindo
    0.68
     aDecoder
    0.60
     tetrach
    0.60
    ">//
    0.59
    MONDAY
    0.59
    Activations Density 0.001%

    No Known Activations