© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 738
    Prev
    Next
    INDEX
    Explanations

    lists of items that use words such as "and", "or", "as", "like", or commas

    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
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -0.82
    either
    -0.71
    HideFlags
    -0.69
    Either
    -0.68
     entweder
    -0.63
     enten
    -0.63
     настолько
    -0.62
     both
    -0.60
     zwar
    -0.59
     soit
    -0.58
    POSITIVE LOGITS
     etc
    2.39
    etc
    1.95
     Etc
    1.73
    Etc
    1.51
     usw
    1.47
     ect
    1.23
    などなど
    1.21
     …)
    1.20
     itp
    1.16
     ...)
    1.15
    Activations Density 0.969%

    No Known Activations