© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7559
    Prev
    Next
    INDEX
    Explanations

    references to the action of assigning or indicating the meaning of a term or item

    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
    Negative Logits
     Verder
    -0.69
     HasFactory
    -0.65
     Kissinger
    -0.65
     BoxFit
    -0.64
    ValueStyle
    -0.63
     Taj
    -0.63
     DAG
    -0.63
    LLocation
    -0.63
    lains
    -0.61
     Daarom
    -0.61
    POSITIVE LOGITS
     denote
    2.39
     denotes
    1.74
     denoted
    1.58
     denoting
    1.58
    Denote
    1.26
     designate
    0.91
    den
    0.90
     Den
    0.83
     designation
    0.82
     designated
    0.79
    Activations Density 0.026%

    No Known Activations