© 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. 15804
    Prev
    Next
    INDEX
    Explanations

    references to time or order of actions, particularly the term "prior to."

    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
     Before
    -0.59
     before
    -0.59
     TILL
    -0.59
    нибудь
    -0.56
     Till
    -0.56
    Before
    -0.55
    PRES
    -0.55
    before
    -0.53
    Till
    -0.52
     until
    -0.52
    POSITIVE LOGITS
    ⓧ
    1.01
    esgue
    0.87
    脚注の使い方
    0.85
    AsUp
    0.81
    tvguidetime
    0.81
    (&:
    0.80
    rän
    0.79
    gucigalpa
    0.78
     Himo
    0.78
     Acton
    0.78
    Activations Density 0.038%

    No Known Activations