© 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. 11297
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters commonly used in programming and markup languages

    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
     estekak
    -0.66
     ProtoMessage
    -0.52
    dotenv
    -0.50
    Referencies
    -0.49
     setuptools
    -0.47
    MessageOf
    -0.47
    исленность
    -0.46
    èdia
    -0.46
     createContext
    -0.46
    insics
    -0.46
    POSITIVE LOGITS
    SequentialGroup
    0.77
     Wikiseite
    0.57
    \{\\
    0.57
    pen
    0.57
     المعيارى
    0.54
    ReusableCell
    0.53
    SuccessListener
    0.53
    ôme
    0.52
     Berufung
    0.52
     CURIAM
    0.51
    Activations Density 0.163%

    No Known Activations