© 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. 0-RES-MATRYOSHKA-DC
    7. 11472
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds and molecules, particularly amino acids, nucleotides, and drug-related structures

    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
     betweenstory
    -0.88
    HtmlAttribute
    -0.71
     @"/
    -0.63
    __*/
    -0.63
    cripcion
    -0.62
    aleigh
    -0.62
    reciated
    -0.62
    WriteLiteral
    -0.61
     "..\..\
    -0.60
     Helens
    -0.60
    POSITIVE LOGITS
    complexContent
    0.78
    cumin
    0.70
     adjust
    0.68
    anine
    0.67
     Alto
    0.65
    Alto
    0.65
     CountDown
    0.64
    mAh
    0.63
    otte
    0.63
     rowspan
    0.62
    Activations Density 0.087%

    No Known Activations