© 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. 22942
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns, likely related to JSON-like data structures or numerical values

    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
    ņš
    -0.67
    endaten
    -0.57
    quehanna
    -0.57
     couteau
    -0.57
     Susquehanna
    -0.55
    CMYK
    -0.54
     Gibbons
    -0.54
     Zem
    -0.53
     eventdata
    -0.53
    Kand
    -0.53
    POSITIVE LOGITS
     InputDecoration
    0.91
    StoryboardSegue
    0.79
     referenties
    0.72
     surla
    0.71
     Orrell
    0.70
    IndentedString
    0.69
    AndEndTag
    0.69
    wards
    0.66
    offsetof
    0.66
    NamedQueries
    0.66
    Activations Density 0.464%

    No Known Activations