© 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. 3-RES-MATRYOSHKA-DC
    7. 3274
    Prev
    Next
    INDEX
    Explanations

    short phrases preceded by or containing the word "a"

    oai_token-act-pair · gemini-2.0-flash
    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
     itſelf
    -0.79
     fubject
    -0.70
     iſt
    -0.69
     Jefus
    -0.69
     pleaſure
    -0.66
     '\\;'
    -0.66
     Efq
    -0.66
     becauſe
    -0.65
     tranſ
    -0.63
     themſelves
    -0.61
    POSITIVE LOGITS
     VIAF
    0.63
    Hentet
    0.57
    DockStyle
    0.56
     chi̍t
    0.54
    Havolalar
    0.51
    unknownFields
    0.50
    AsUp
    0.48
     препратки
    0.48
     rhestr
    0.47
     createContext
    0.47
    Activations Density 0.689%

    No Known Activations