© 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. 14710
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and their significance in 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
     CreateTagHelper
    -0.52
    ಾದ
    -0.51
     acrylique
    -0.48
     Chloride
    -0.47
    jes
    -0.45
    Климат
    -0.45
     Halen
    -0.45
    ukone
    -0.43
    park
    -0.43
    ("\\
    -0.43
    POSITIVE LOGITS
     '\\;'
    0.81
    AutoScale
    0.69
    Hochspringen
    0.64
    MLLoader
    0.63
     للاسماء
    0.63
    StoryboardSegue
    0.60
    رشف
    0.60
    ترل
    0.59
    Portale
    0.59
    AxisAlignment
    0.59
    Activations Density 0.009%

    No Known Activations