© 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. 25012
    Prev
    Next
    INDEX
    Explanations

    closed brackets or specific delimiters in a structured format, possibly indicating the end of data entries or code segments

    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
    Negative Logits
    tagHelperRunner
    -0.76
    principalColumn
    -0.69
    spesies
    -0.67
    ressible
    -0.59
     beginnetje
    -0.54
     ProtoMessage
    -0.54
     produisons
    -0.54
    InvalidProtocol
    -0.53
     विश्वसनीयता
    -0.53
    expandindo
    -0.51
    POSITIVE LOGITS
    ValueStyle
    0.60
    ={()
    0.53
    الإنجليزية
    0.52
    AndEndTag
    0.50
    uali
    0.45
    enggarakan
    0.45
    Referències
    0.44
    cherichia
    0.43
    ptian
    0.43
    SPJ
    0.43
    Activations Density 0.019%

    No Known Activations