© 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. 4296
    Prev
    Next
    INDEX
    Explanations

    specific instances of pronouns referring to people

    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
    PageModule
    -0.52
     AssemblyCulture
    -0.51
    tha
    -0.48
    laştır
    -0.48
    >--}}
    -0.47
    per
    -0.45
    }$-
    -0.43
     Gm
    -0.43
    Aiheesta
    -0.43
     Audiodateien
    -0.43
    POSITIVE LOGITS
     FetchType
    0.68
    uanya
    0.67
     виправивши
    0.63
     antaranya
    0.63
    preuve
    0.61
    rovnik
    0.61
     autorytatywna
    0.60
     getItemCount
    0.59
    fficients
    0.59
    melan
    0.59
    Activations Density 0.194%

    No Known Activations