© 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. 100
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be" used in all tenses

    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
     Efq
    -0.93
     Houſe
    -0.90
     Chriftian
    -0.89
     themſelves
    -0.84
     Theſe
    -0.83
     itſelf
    -0.82
     Majefty
    -0.82
    GEBURTSDATUM
    -0.81
     fubject
    -0.80
     betweenstory
    -0.79
    POSITIVE LOGITS
     not
    1.00
     got
    0.84
     also
    0.82
     am
    0.81
     a
    0.79
     are
    0.78
     currently
    0.75
     all
    0.71
     now
    0.68
     pretty
    0.68
    Activations Density 4.095%

    No Known Activations