© 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. 3-RES-MATRYOSHKA-DC
    7. 121
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and adjectives.

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Athenians
    -0.75
     Persians
    -0.71
    נטרנט
    -0.67
     ää
    -0.66
     vectorielles
    -0.64
     Pliny
    -0.64
     Puritans
    -0.64
     Agamemnon
    -0.63
     Swedes
    -0.63
     negroes
    -0.62
    POSITIVE LOGITS
     his
    2.03
     their
    1.98
     her
    1.95
     our
    1.88
     your
    1.81
     own
    1.77
    their
    1.63
     my
    1.61
     THEIR
    1.59
    Their
    1.55
    Activations Density 2.573%

    No Known Activations