© 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. 6573
    Prev
    Next
    INDEX
    Explanations

    data related to molecular structures, chemical compositions, or chemical data

    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
    出版年
    -0.82
    ◀
    -0.72
     CITED
    -0.69
     starved
    -0.69
     characterize
    -0.66
     signaling
    -0.65
     intact
    -0.64
    poptosis
    -0.64
    Tikang
    -0.64
     purified
    -0.61
    POSITIVE LOGITS
    EndGlobalSection
    0.57
     Rè
    0.56
    AsStream
    0.54
    AddWithValue
    0.52
    InstanceState
    0.52
     imprend
    0.52
     bicarbon
    0.51
    AndEndTag
    0.50
     SqlCommand
    0.50
     мәкал
    0.49
    Activations Density 3.790%

    No Known Activations