© 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. 15301
    Prev
    Next
    INDEX
    Explanations

    expressions of luck or favorable circumstances

    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
    Not in Any Lists

    No Comments

    Negative Logits
    mappedBy
    -0.91
     disambiguazione
    -0.81
     snippetHide
    -0.76
     substring
    -0.68
    ########.
    -0.68
     Vikipedi
    -0.64
    RTEE
    -0.64
    tvguidetime
    -0.63
    :✨
    -0.62
     كومونز
    -0.62
    POSITIVE LOGITS
     Luckily
    0.71
    Luckily
    0.69
    Fortunately
    0.68
     Fortunately
    0.65
    Thankfully
    0.59
     Thankfully
    0.59
     fortunately
    0.58
     luckily
    0.57
    好在
    0.56
    fortunately
    0.53
    Activations Density 0.016%

    No Known Activations