© 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. 29489
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and birth order

    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
    授
    -0.42
    data
    -0.42
     mies
    -0.42
    loading
    -0.42
    resolvers
    -0.39
    кре
    -0.39
    новништво
    -0.39
     lais
    -0.39
    ра
    -0.38
     nơi
    -0.38
    POSITIVE LOGITS
     nahilalakip
    1.09
    ]")]
    0.91
     pinulongan
    0.78
     Савезне
    0.75
    ChildScrollView
    0.75
     ModelExpression
    0.75
     alphabetically
    0.73
    })*/
    0.72
    XmlAccessorType
    0.71
    AddTagHelper
    0.71
    Activations Density 0.008%

    No Known Activations