© 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. 3760
    Prev
    Next
    INDEX
    Explanations

    commands and elements related to programming and server configurations

    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
     Knud
    -0.44
    unov
    -0.44
     Miet
    -0.41
     tu
    -0.41
    hing
    -0.40
    marche
    -0.40
     WorldCat
    -0.39
    бурга
    -0.39
    Gpio
    -0.39
    gerufen
    -0.39
    POSITIVE LOGITS
    oa̍t
    0.94
     AssemblyCompany
    0.89
    RunAsync
    0.87
     <=",
    0.82
    +#+#
    0.80
    AndroidJUnit
    0.76
    AndEndTag
    0.75
    StructEnd
    0.74
    queryInterface
    0.74
    MigrationBuilder
    0.73
    Activations Density 0.082%

    No Known Activations