© 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. 17256
    Prev
    Next
    INDEX
    Explanations

    a shift or contrast in ideas or statements

    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
    Publié
    -0.56
     الرياضيه
    -0.55
     ideia
    -0.54
    pires
    -0.51
    帖最后由
    -0.51
    ubb
    -0.50
    Birth
    -0.49
     Boyer
    -0.49
    Ooooo
    -0.49
     nahilalakip
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.76
    memoized
    0.72
    ValueGeneration
    0.61
    endphp
    0.61
    WireFormatLite
    0.59
    rungsseite
    0.57
    ::_('
    0.56
    derry
    0.54
     concorso
    0.54
    csol
    0.52
    Activations Density 0.014%

    No Known Activations