© 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. 3417
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various contexts

    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
     EconPapers
    -1.02
    ValueStyle
    -0.92
    MigrationBuilder
    -0.91
    yntaxException
    -0.87
    Portale
    -0.86
     مشين
    -0.85
    UnusedPrivate
    -0.85
    tagHelperRunner
    -0.83
    BufferException
    -0.81
     мәкал
    -0.81
    POSITIVE LOGITS
    nis
    0.48
     Is
    0.47
    is
    0.45
    Is
    0.44
     Was
    0.44
     épaules
    0.42
     double
    0.42
    Was
    0.40
     tailles
    0.40
     Mar
    0.39
    Activations Density 0.132%

    No Known Activations