© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8409
    Prev
    Next
    INDEX
    Explanations

    specific forms of punctuation or sentence endings

    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
    mybatisplus
    -0.91
     الرياضيه
    -0.88
     يتيمه
    -0.84
     Wallflower
    -0.78
    脚注の使い方
    -0.77
    ⓧ
    -0.74
    printStackTrace
    -0.73
     المعيارى
    -0.71
    ISupport
    -0.71
    
    -0.70
    POSITIVE LOGITS
     auxquels
    0.62
    賀状
    0.55
     auxquelles
    0.54
     
    0.54
     atención
    0.51
    koma
    0.49
     côtes
    0.49
     couverte
    0.49
     mennes
    0.48
     गो
    0.48
    Activations Density 0.004%

    No Known Activations