© 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. 1412
    Prev
    Next
    INDEX
    Explanations

    the word "as" followed by an article and then another word that describes or renames the prior noun to it.

    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
     stated
    -0.67
     said
    -0.60
     mentioned
    -0.59
     told
    -0.57
     noted
    -0.56
     cited
    -0.56
     specified
    -0.54
     asked
    -0.54
     quoted
    -0.52
     several
    -0.50
    POSITIVE LOGITS
     étant
    1.20
     belonging
    1.10
     fiind
    1.07
     sendo
    1.02
    being
    1.02
     being
    1.02
    having
    0.99
    belong
    0.99
     having
    0.94
     appartenant
    0.91
    Activations Density 0.714%

    No Known Activations