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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16261
    Prev
    Next
    INDEX
    Explanations

    descriptions of laboratory procedures and sample handling in scientific experiments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.87
    tvguidetime
    -0.72
    VersionUID
    -0.70
    CodeAttribute
    -0.68
    >*/
    -0.68
    UnusedPrivate
    -0.65
    #
    -0.65
    WithIOException
    -0.65
    protoimpl
    -0.65
    reportWebVitals
    -0.65
    POSITIVE LOGITS
     valamint
    0.50
     alliés
    0.49
     namin
    0.48
     benessere
    0.48
     glycerin
    0.47
     géographique
    0.47
     sonno
    0.46
     Trials
    0.46
    رأة
    0.45
     disposição
    0.45
    Activations Density 0.071%

    No Known Activations