© 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. 27211
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating time or chronology

    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
    webElement
    -0.82
    üedad
    -0.56
     möge
    -0.55
    kmal
    -0.54
     upcoming
    -0.53
    dshaw
    -0.53
     caufe
    -0.53
    南浔
    -0.52
    gency
    -0.52
    gemene
    -0.51
    POSITIVE LOGITS
    enumi
    0.82
    enumii
    0.65
    previous
    0.55
     previous
    0.53
     Previous
    0.49
     précédent
    0.49
    ందు
    0.49
     précédentes
    0.49
    Previous
    0.48
     vorige
    0.48
    Activations Density 0.219%

    No Known Activations