© 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. 7097
    Prev
    Next
    INDEX
    Explanations

    references to a specific phospholipid, namely palmitoyl-phosphatidylcholine (POP C), or terms related to this molecule

    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
     Perugia
    -0.63
    ocino
    -0.61
     Potter
    -0.59
     Lima
    -0.58
    BRL
    -0.58
     Vard
    -0.57
    lotl
    -0.56
     Пер
    -0.54
    ://
    -0.54
    Aves
    -0.54
    POSITIVE LOGITS
     pal
    3.36
    Pal
    3.22
     Pal
    3.16
    pal
    3.14
     PAL
    2.61
    PAL
    2.52
     palate
    1.63
     Palatine
    1.59
     pall
    1.48
    ypal
    1.48
    Activations Density 0.020%

    No Known Activations