© 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. 3849
    Prev
    Next
    INDEX
    Explanations

    references to the chemical motif "tri" or "tri" prefix indicating chemical groups or compounds

    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
    tr
    -1.01
    TR
    -0.91
     TR
    -0.88
     tr
    -0.86
     Tr
    -0.82
    Tr
    -0.77
    TRC
    -0.67
    المراجع
    -0.66
    trs
    -0.60
    trc
    -0.56
    POSITIVE LOGITS
     tri
    2.61
     Tri
    1.73
    Tri
    1.72
    tri
    1.63
     TRI
    1.04
    Tril
    0.98
     Trich
    0.92
    Trich
    0.85
    دانشنامهٔ
    0.84
    TRI
    0.84
    Activations Density 0.004%

    No Known Activations