© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    terms related to programming elements, particularly objects and database components

    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
     AssemblyCulture
    -0.60
    EndInit
    -0.54
    atchewan
    -0.51
    VIAF
    -0.49
    RectangleBorder
    -0.46
    ValueGenerated
    -0.45
     buhay
    -0.45
    itaire
    -0.44
    tableFuture
    -0.44
    setPointSize
    -0.44
    POSITIVE LOGITS
     Мексичка
    0.66
     >=",
    0.64
     forfeited
    0.61
    vikle
    0.60
     Signalez
    0.59
    انجليز
    0.59
     näin
    0.58
    glises
    0.56
    soever
    0.54
     <",
    0.54
    Activations Density 0.491%

    No Known Activations