© 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. 3099
    Prev
    Next
    INDEX
    Explanations

    common short function words in sentences, like "of", "the", and "for".

    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
    SequentialGroup
    -0.76
     Italijanski
    -0.72
     виправивши
    -0.70
     AssemblyCompany
    -0.67
    HtmlAttribute
    -0.64
    FormsModule
    -0.62
    Portály
    -0.61
     satunya
    -0.59
    二是
    -0.59
     AssemblyTitle
    -0.58
    POSITIVE LOGITS
     various
    1.45
    various
    1.43
     Various
    1.38
     different
    1.35
    Various
    1.32
     Different
    1.21
    different
    1.21
    Different
    1.21
     différents
    1.20
     différentes
    1.19
    Activations Density 0.947%

    No Known Activations