© 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. 16178
    Prev
    Next
    INDEX
    Explanations

    occurrences of the tab character, indicating sections of structured data or lists

    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
    PositiveButton
    -0.54
     various
    -0.53
    recover
    -0.51
    det
    -0.50
     typical
    -0.50
    qui
    -0.50
     varying
    -0.50
    AROUND
    -0.49
     small
    -0.47
     equally
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.88
    ReusableCell
    0.85
    ItemBackground
    0.80
    WebElementEntity
    0.79
     Efq
    0.75
    adaptiveStyles
    0.75
     cherchés
    0.71
    LabelTagHelper
    0.69
    HandlerContext
    0.69
     незавершена
    0.67
    Activations Density 0.085%

    No Known Activations