© 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. 9787
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their placements in the text

    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
     AssemblyTitle
    -0.86
    AnchorStyles
    -0.82
     مشين
    -0.79
     EconPapers
    -0.78
     arşivlendi
    -0.75
    HasAnnotation
    -0.67
     snippetHide
    -0.65
    WebServlet
    -0.65
    extAlignment
    -0.65
    photobucket
    -0.65
    POSITIVE LOGITS
    Gweler
    0.59
     resourceCulture
    0.52
    Aiheesta
    0.51
     führten
    0.51
     palmas
    0.49
     '..
    0.49
    ,:,
    0.47
    Quack
    0.47
     Ramsay
    0.47
     psycopg
    0.46
    Activations Density 0.035%

    No Known Activations