© 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. 0-RES-MATRYOSHKA-DC
    7. 12178
    Prev
    Next
    INDEX
    Explanations

    the presence or usage of a specific form of the verb "to be" in the text

    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
     HttpNotFound
    -0.54
    Демографія
    -0.49
    شفى
    -0.49
    tbx
    -0.47
    vt
    -0.47
     initComponents
    -0.46
    vg
    -0.44
    ATAN
    -0.44
     Chry
    -0.44
     bly
    -0.43
    POSITIVE LOGITS
     VB
    2.44
    VB
    2.28
     vb
    1.84
    vb
    1.66
    Vb
    0.95
    
    0.82
    Datuak
    0.78
    MENAFN
    0.73
    libft
    0.66
     propOrder
    0.66
    Activations Density 0.004%

    No Known Activations