© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15805
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific pattern of repeatable algebraic structures encoded by matrices

    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
     r
    -0.72
    //*[@
    -0.59
     initState
    -0.52
     Alton
    -0.52
     next
    -0.52
    VolleyError
    -0.52
     Afonso
    -0.51
    ifax
    -0.51
    quale
    -0.50
    getItemId
    -0.48
    POSITIVE LOGITS
    UnusedPrivate
    0.76
     getRule
    0.65
    ритори
    0.63
    IContainer
    0.59
     tâche
    0.59
    kháu
    0.59
    tangentMode
    0.59
     stør
    0.57
    ThroughAttribute
    0.57
     AllAfrica
    0.56
    Activations Density 0.044%

    No Known Activations