© 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. 20809
    Prev
    Next
    INDEX
    Explanations

    nested array structures or list-like formats in data

    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
    SpringBootTest
    -1.05
    fillType
    -1.03
    consulté
    -0.98
     AssemblyCompany
    -0.98
    HasForeignKey
    -0.92
     ModelExpression
    -0.92
    RenderAtEndOf
    -0.91
     StringTokenizer
    -0.90
    ScopeManager
    -0.88
    webElementXpaths
    -0.88
    POSITIVE LOGITS
    比如
    0.52
    みや
    0.52
     laude
    0.50
    最快更新
    0.49
     matplotlib
    0.49
     относятся
    0.46
    astie
    0.45
     Shrub
    0.45
    jén
    0.45
    topatho
    0.45
    Activations Density 0.027%

    No Known Activations