© 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. 217
    Prev
    Next
    INDEX
    Explanations

    pronouns followed or preceded by the verb to be

    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
     is
    -0.73
    zieży
    -0.63
     nytt
    -0.62
     которому
    -0.61
     itself
    -0.60
     was
    -0.59
     dítě
    -0.58
     vrijwilli
    -0.58
    was
    -0.57
     isn
    -0.56
    POSITIVE LOGITS
     themselves
    2.05
    themselves
    1.90
    Their
    1.32
     yourselves
    1.31
     Their
    1.25
     themſelves
    1.21
     mereka
    1.20
     they
    1.18
     their
    1.17
     Mereka
    1.16
    Activations Density 2.952%

    No Known Activations