© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14019
    Prev
    Next
    INDEX
    Explanations

    quotes and different types of string delimiters in a JSON structure

    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
    fromnode
    -0.74
     Roskov
    -0.69
    SequentialGroup
    -0.66
    ніципалі
    -0.66
    numerusform
    -0.65
     يتيمه
    -0.64
    DeleteBehavior
    -0.64
    protoimpl
    -0.63
     surla
    -0.63
    хьтан
    -0.63
    POSITIVE LOGITS
    gheny
    0.49
     answers
    0.49
     seduta
    0.49
     steg
    0.47
     infused
    0.47
    ainville
    0.47
    ategorias
    0.47
    annin
    0.46
    strptime
    0.45
     isEqualToString
    0.45
    Activations Density 0.031%

    No Known Activations