© 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. 22-RES-MATRYOSHKA-DC
    7. 3133
    Prev
    Next
    INDEX
    Explanations

    general words that can go before or after a noun or adjective, such as "a", "of", "and", and "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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     keuangan
    -0.52
     mencionado
    -0.46
     notoriously
    -0.46
     frequentemente
    -0.46
     famously
    -0.44
    onAttach
    -0.44
     hned
    -0.44
     siis
    -0.44
     teda
    -0.44
     above
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.88
     AssemblyProduct
    0.81
     darkness
    0.76
    expandindo
    0.74
     truth
    0.73
    ChildScrollView
    0.70
    GEBURTSDATUM
    0.69
    ViewChild
    0.69
    moment
    0.67
    principalColumn
    0.67
    Activations Density 0.702%

    No Known Activations