© 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. 67
    Prev
    Next
    INDEX
    Explanations

    occurrences of forms of 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
     Jefus
    -1.02
     purpoſe
    -1.00
     itſelf
    -1.00
     poffible
    -0.98
     ſtate
    -0.96
     pleaſure
    -0.96
     ingrat
    -0.96
     chofe
    -0.94
     habet
    -0.94
     consecration
    -0.92
    POSITIVE LOGITS
     be
    1.88
     being
    1.24
     Be
    1.21
     être
    1.15
     shouldBe
    1.10
     бъдат
    1.09
     were
    1.08
    ToBe
    1.06
    tobe
    1.05
     BE
    1.02
    Activations Density 4.576%

    No Known Activations