© 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. 0-RES-MATRYOSHKA-DC
    7. 13827
    Prev
    Next
    INDEX
    Explanations

    patterns of specialized computer code or identifiers, often characterized by specific structured symbols, abbreviations, or formatting conventions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GORITH
    -0.59
    JspWriter
    -0.57
     II
    -0.56
     fiducia
    -0.56
    jMenuItem
    -0.55
    ={()
    -0.54
     ICP
    -0.54
    IPLE
    -0.53
     AI
    -0.53
    AIP
    -0.52
    POSITIVE LOGITS
    LU
    1.69
     LU
    1.65
     RU
    1.47
     MU
    1.44
     BU
    1.41
    BU
    1.41
    MU
    1.33
    RU
    1.30
     KU
    1.09
    JU
    1.02
    Activations Density 0.002%

    No Known Activations