© 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. 3517
    Prev
    Next
    INDEX
    Explanations

    visual representations and scaling information in experimental 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
    Yes
    -0.48
    yes
    -0.46
    true
    -0.42
    esp
    -0.42
    O
    -0.42
     музей
    -0.41
     Yes
    -0.41
    -
    -0.40
     YES
    -0.40
     ting
    -0.40
    POSITIVE LOGITS
    PreferredItem
    0.80
    HasAnnotation
    0.80
    ]--;
    0.79
    UTERS
    0.74
    MemoryWarning
    0.71
    ulipas
    0.70
     StatefulWidget
    0.68
     AssemblyCulture
    0.68
     ویکی‌پدیای
    0.66
    TypedDataSet
    0.66
    Activations Density 0.008%

    No Known Activations