© 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. 9493
    Prev
    Next
    INDEX
    Explanations

    references to time periods following a significant event, particularly focusing on the term "post."

    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
    \{\\
    -0.74
    ępnie
    -0.54
    ünkü
    -0.51
    {§
    -0.51
     Générale
    -0.49
    rittura
    -0.49
     REA
    -0.49
     Generale
    -0.47
    ’
    -0.47
    Bef
    -0.47
    POSITIVE LOGITS
     Roskov
    0.86
    gelopen
    0.77
    دانشنامهٔ
    0.75
    ьаж
    0.71
    Gambas
    0.71
     kaarangay
    0.69
    hésite
    0.67
    حوالہ
    0.67
     FishBase
    0.66
    shadowOffset
    0.66
    Activations Density 0.008%

    No Known Activations