© 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. 17196
    Prev
    Next
    INDEX
    Explanations

    instances of the word "error."

    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
     itſelf
    -0.66
    بوابة
    -0.61
     poffe
    -0.61
     pleaſure
    -0.60
     raiſ
    -0.60
     myſelf
    -0.59
     houſe
    -0.57
     nonUne
    -0.57
     nakalista
    -0.56
     Efq
    -0.56
    POSITIVE LOGITS
     zug
    0.63
    setLong
    0.56
    ggior
    0.55
     CascadeType
    0.55
    oplasty
    0.54
    存于互联网档案馆
    0.51
    __*/
    0.51
    tesse
    0.50
    styleable
    0.50
    WebElementEntity
    0.49
    Activations Density 0.002%

    No Known Activations