© 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. 18271
    Prev
    Next
    INDEX
    Explanations

    phrases related to making requests or expressing desires

    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
     Mund
    -0.57
    ちゃう
    -0.52
    AttributeSet
    -0.52
     halben
    -0.52
    ixon
    -0.51
     Huber
    -0.51
    สุข
    -0.51
    落ちる
    -0.51
    しまう
    -0.50
    あっという
    -0.50
    POSITIVE LOGITS
    AsUp
    0.78
     calendriers
    0.75
    లాలు
    0.74
    WriteTagHelper
    0.73
    IMDG
    0.72
     تضيفلها
    0.71
    ChildIndex
    0.71
     ModelExpression
    0.69
     icmp
    0.69
    ={()=>
    0.69
    Activations Density 0.004%

    No Known Activations