© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5644
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns indicating ownership or attribution

    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
     ddelweddau
    -0.70
    Datuak
    -0.67
    altham
    -0.67
     ModelRenderer
    -0.65
     Lokales
    -0.64
    Personensuche
    -0.64
     Lightboxes
    -0.63
     sóc
    -0.62
    ='';
    -0.60
    XmlAttribute
    -0.60
    POSITIVE LOGITS
     whose
    2.28
    whose
    2.08
     Whose
    1.98
    Whose
    1.87
     whofe
    1.77
     cuyos
    1.64
     cuyas
    1.63
     cuya
    1.57
     cuyo
    1.56
     whoſe
    1.52
    Activations Density 0.007%

    No Known Activations