© 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. 24-RES-MATRYOSHKA-DC
    7. 1609
    Prev
    Next
    INDEX
    Explanations

    the word "do" followed by another short article such as "the"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     متعلقه
    -0.81
    原始内容存档于
    -0.72
    httphttps
    -0.66
    Искәрмәләр
    -0.64
    SuccessListener
    -0.63
     betweenstory
    -0.62
    νώ
    -0.61
    TargetException
    -0.60
    layui
    -0.59
     насељу
    -0.59
    POSITIVE LOGITS
     something
    0.71
     harm
    0.69
     likewise
    0.69
    omsday
    0.68
     justice
    0.67
     nothing
    0.64
     damage
    0.64
     things
    0.64
     penance
    0.64
     so
    0.60
    Activations Density 0.399%

    No Known Activations