© 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. 8267
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or associations

    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
     both
    -0.71
     between
    -0.63
     mellom
    -0.58
     mellan
    -0.57
     BETWEEN
    -0.56
    devamını
    -0.55
    both
    -0.54
    between
    -0.54
     Between
    -0.52
     zwischen
    -0.52
    POSITIVE LOGITS
     Efq
    1.08
    RectangleBorder
    0.84
     Majefty
    0.84
    EndContext
    0.82
     Monfieur
    0.82
     auffi
    0.80
     becauſe
    0.79
     fhew
    0.79
    verwijspagina
    0.79
     leſs
    0.78
    Activations Density 0.020%

    No Known Activations