© 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. 22404
    Prev
    Next
    INDEX
    Explanations

    instances of the word "been" and its variations in different contexts

    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
     aliqu
    -0.55
    ้อย
    -0.54
    IGraphics
    -0.53
    mıştır
    -0.52
    medim
    -0.52
    ļa
    -0.50
    baguna
    -0.50
     ziel
    -0.50
    testo
    -0.48
    Expressions
    -0.48
    POSITIVE LOGITS
     Савезне
    0.96
    ✨:
    0.84
    исленность
    0.79
    InputBorder
    0.77
    {\"
    0.71
     OMIT
    0.70
    Autoritní
    0.69
    JoinTable
    0.67
     alike
    0.66
    SharedDtor
    0.66
    Activations Density 0.021%

    No Known Activations