© 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. 9386
    Prev
    Next
    INDEX
    Explanations

    references to time-related phrases

    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
     varandra
    -0.77
    riwal
    -0.73
     Obrador
    -0.63
    //
    -0.54
    koda
    -0.53
    tomos
    -0.52
    Geplaatst
    -0.51
    asanjo
    -0.51
     prohibido
    -0.50
    ebbe
    -0.50
    POSITIVE LOGITS
    CHREIB
    0.76
    URDAY
    0.72
    شهاد
    0.71
    udadera
    0.71
    esterday
    0.70
     BRARY
    0.68
    ntown
    0.67
     *++
    0.65
    uesday
    0.65
    terday
    0.65
    Activations Density 0.022%

    No Known Activations