© 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. 6-RES-MATRYOSHKA-DC
    7. 423
    Prev
    Next
    INDEX
    Explanations

    the pronoun "he" followed by a verb

    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
    EUROPA
    -0.60
     our
    -0.58
     accesso
    -0.57
    seamnă
    -0.57
    zyw
    -0.56
    Dzi
    -0.55
    wsze
    -0.55
    our
    -0.54
    ouc
    -0.54
    thora
    -0.53
    POSITIVE LOGITS
     himself
    2.00
    himself
    1.80
     Himself
    1.68
     his
    1.52
    He
    1.47
     he
    1.41
    His
    1.41
     He
    1.38
    his
    1.34
     she
    1.29
    Activations Density 1.721%

    No Known Activations