© 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. 9344
    Prev
    Next
    INDEX
    Explanations

    terms related to effects or actions influenced by conditions or states

    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
    MessageTagHelper
    -0.79
    ValueStyle
    -0.75
    webElementXpaths
    -0.74
     préféré
    -0.68
     åt
    -0.66
     tecnolog
    -0.65
    improved
    -0.65
     itſelf
    -0.65
    曖昧さ回避
    -0.64
     frumos
    -0.64
    POSITIVE LOGITS
     out
    0.48
     absolut
    0.47
     KI
    0.46
    
    0.44
    ($__
    0.43
    BeginContext
    0.43
     hold
    0.42
    בור
    0.42
    él
    0.41
    irvana
    0.41
    Activations Density 0.033%

    No Known Activations