© 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. 9474
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or expressions within the text

    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
    blanc
    -0.79
     Penh
    -0.78
     AssemblyCulture
    -0.77
    öl
    -0.75
    %)$
    -0.74
    Slf
    -0.73
    hagic
    -0.69
     ?>>
    -0.68
     kep
    -0.66
    ()];
    -0.66
    POSITIVE LOGITS
     phrases
    1.57
     phrase
    1.51
     Phrase
    1.47
     Phrases
    1.38
    phrase
    1.36
    Phrase
    1.31
    phrases
    1.30
     frase
    1.07
     PHR
    1.04
    rases
    1.03
    Activations Density 0.003%

    No Known Activations