© 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. 6164
    Prev
    Next
    INDEX
    Explanations

    descriptions of conserved motifs or regions in protein sequences

    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
    ГЛА
    -0.54
     مز
    -0.54
    Settle
    -0.52
     Contin
    -0.52
     zb
    -0.51
     congen
    -0.49
    Multipart
    -0.48
     Relay
    -0.48
     Schult
    -0.48
    igshid
    -0.47
    POSITIVE LOGITS
     conserved
    2.73
     conservation
    2.48
     Conservation
    2.34
    conservation
    2.34
     conserv
    2.28
    Conservation
    2.28
     CONSERV
    2.28
     conservative
    2.16
     CONSERVATION
    2.16
    conserv
    2.13
    Activations Density 0.018%

    No Known Activations