© 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. 17053
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and words that highlight contrasts or distinctions

    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
     testGet
    -0.51
    jface
    -0.50
     per
    -0.47
    stdlib
    -0.46
    uruhan
    -0.46
    createObject
    -0.45
     Cuth
    -0.43
     کنه
    -0.42
    logrus
    -0.42
     בש
    -0.41
    POSITIVE LOGITS
    BeginContext
    0.85
    rungsseite
    0.76
     OFDb
    0.75
     referenties
    0.75
     дописавши
    0.71
    IVEREF
    0.71
     AssemblyCulture
    0.69
    RunAsync
    0.69
    memoized
    0.68
    afficheront
    0.68
    Activations Density 0.082%

    No Known Activations