© 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. 20104
    Prev
    Next
    INDEX
    Explanations

    the presence of various types of parentheses and quotation marks 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
    eger
    -0.57
    hooter
    -0.55
    __.__
    -0.54
    iedler
    -0.54
     tem
    -0.52
     Starr
    -0.52
     Spiel
    -0.51
    ništ
    -0.51
     Nath
    -0.49
     Seidel
    -0.48
    POSITIVE LOGITS
     Majefty
    0.82
     Cæsar
    0.80
     Efq
    0.79
     "\<
    0.74
     kubwa
    0.73
    erçe
    0.72
     fhort
    0.71
     Shakspeare
    0.71
    ंदीखरीदारी
    0.70
     itſelf
    0.70
    Activations Density 0.019%

    No Known Activations