© 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. 13875
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information regarding health and demographics

    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
     Theſe
    -0.69
     firſt
    -0.63
     purpoſe
    -0.63
     imidlertid
    -0.61
     ſmall
    -0.61
     Anſ
    -0.58
     greateſt
    -0.58
     myſelf
    -0.58
     ſtate
    -0.57
     beſ
    -0.57
    POSITIVE LOGITS
    complexContent
    0.80
    BeginInit
    0.79
    WriteBarrier
    0.75
    setVerticalGroup
    0.73
    GEBURTSDATUM
    0.71
     Waray
    0.69
    MockMvc
    0.68
    StoryboardSegue
    0.67
    VersionUID
    0.65
    richTextPanel
    0.65
    Activations Density 1.673%

    No Known Activations