© 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. 986
    Prev
    Next
    INDEX
    Explanations

    sentences in the passive voice and imperative clauses

    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
     AssemblyTitle
    -0.67
     StatefulWidget
    -0.65
     &___
    -0.59
     AssemblyProduct
    -0.58
     estimés
    -0.57
    êques
    -0.55
    )++;
    -0.54
     للمعارف
    -0.54
    abetes
    -0.53
    zzleHttp
    -0.52
    POSITIVE LOGITS
     removal
    2.08
     removed
    2.02
     remove
    1.91
     removing
    1.85
     Removal
    1.83
     REMOV
    1.70
     Removing
    1.69
    removal
    1.69
     Remove
    1.67
     delete
    1.64
    Activations Density 3.580%

    No Known Activations