© 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. 4029
    Prev
    Next
    INDEX
    Explanations

    references to the collective pronouns indicating discussions about groups or individuals within a social context

    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
     ſeveral
    -0.81
     themſelves
    -0.67
     Efq
    -0.65
     ſhe
    -0.61
     himſelf
    -0.61
     Diſ
    -0.61
     whoſe
    -0.59
     noastră
    -0.56
     Jefus
    -0.56
     Monfieur
    -0.56
    POSITIVE LOGITS
    UnknownFieldSet
    0.88
    contentLoaded
    0.86
    RegressionTest
    0.78
    Geplaatst
    0.75
    ьаж
    0.75
    expandindo
    0.74
     Whilst
    0.71
    findpost
    0.71
    complexContent
    0.69
    LookAnd
    0.69
    Activations Density 0.363%

    No Known Activations