© 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. 10643
    Prev
    Next
    INDEX
    Explanations

    the repeated phrase "effects of" in relation to various subjects

    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
     فريبيس
    -0.71
    setVerticalGroup
    -0.54
    ContentAlignment
    -0.51
    ...</
    -0.49
     AttributeSet
    -0.48
     onBind
    -0.48
     שוליים
    -0.46
    bray
    -0.46
     للمعارف
    -0.46
     isInitialized
    -0.45
    POSITIVE LOGITS
    mtd
    0.71
     pleaſure
    0.70
     ſeveral
    0.67
    estacks
    0.67
     Period
    0.66
     Sins
    0.66
     Sheen
    0.66
    Period
    0.66
     Nebula
    0.65
     Stacks
    0.65
    Activations Density 0.019%

    No Known Activations