© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    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
     Copyright
    -0.51
     cap
    -0.45
    AspNetCore
    -0.45
     seni
    -0.43
    bara
    -0.42
    endio
    -0.41
    Архи
    -0.41
     c
    -0.41
     autor
    -0.40
     Apes
    -0.40
    POSITIVE LOGITS
    IsMutable
    0.97
    QMetaType
    0.97
     itſelf
    0.90
    awtextra
    0.84
    exitRule
    0.83
    OrBuilder
    0.82
     myſelf
    0.80
    يكب
    0.79
    oneofs
    0.79
     neceff
    0.78
    Activations Density 0.001%

    No Known Activations