© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6142
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "paper"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     BoxFit
    -0.80
    FormTagHelper
    -0.78
    paravant
    -0.74
    rescence
    -0.73
    DataAnnotations
    -0.71
     CWE
    -0.71
    ]--;
    -0.71
     betweenstory
    -0.71
    {{/
    -0.71
     Glance
    -0.69
    POSITIVE LOGITS
     PAPER
    1.80
     Paper
    1.72
    Paper
    1.68
     paper
    1.66
     Papers
    1.61
    paper
    1.60
    PAPER
    1.59
     papers
    1.50
     PAPERS
    1.50
    Papers
    1.35
    Activations Density 0.030%

    No Known Activations