© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 143
    Prev
    Next
    INDEX
    Explanations

    the word "be" or forms of "be" (is, are, been, etc.) in close proximity to other content words.

    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/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réalis
    -0.79
     überlegen
    -0.77
    catching
    -0.69
    locating
    -0.67
    selecting
    -0.64
     suspending
    -0.64
    knew
    -0.63
     anhänger
    -0.62
     purpoſe
    -0.62
     burying
    -0.61
    POSITIVE LOGITS
     brought
    0.96
     taken
    0.95
     processed
    0.90
     treated
    0.89
     handled
    0.88
     delivered
    0.88
     transferred
    0.88
     dealt
    0.87
     placed
    0.87
     analyzed
    0.85
    Activations Density 4.769%

    No Known Activations