© 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. 7572
    Prev
    Next
    INDEX
    Explanations

    references to specific individual or pronoun references

    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
    rativa
    -0.59
    GraphicsUnit
    -0.56
     Edg
    -0.51
    onAttach
    -0.49
     Raoul
    -0.47
     Theſe
    -0.47
    numerusform
    -0.46
    board
    -0.45
    PageRoute
    -0.45
    RRect
    -0.45
    POSITIVE LOGITS
    titleMargin
    0.60
     intptr
    0.60
     indisponible
    0.59
     varandra
    0.59
    hysema
    0.58
    ITAT
    0.57
    LabelTagHelper
    0.57
     كومونز
    0.57
    ffion
    0.56
    cussed
    0.56
    Activations Density 0.396%

    No Known Activations