© 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. 3417
    Prev
    Next
    INDEX
    Explanations

    pronouns that take the place of a group of people

    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
     I
    -0.57
     descrit
    -0.47
    を受けた
    -0.47
     my
    -0.47
    dian
    -0.46
    ACY
    -0.45
     myself
    -0.44
    gares
    -0.44
    acity
    -0.43
     present
    -0.43
    POSITIVE LOGITS
    CloseOperation
    1.16
     themſelves
    1.10
     Efq
    1.06
     itſelf
    1.06
     Shakspeare
    1.05
     Shaksp
    1.01
     Monfieur
    0.99
    NameInMap
    0.97
    StoryboardSegue
    0.95
     Theſe
    0.94
    Activations Density 0.243%

    No Known Activations