© 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. 20119
    Prev
    Next
    INDEX
    Explanations

    responses related to technical help or troubleshooting

    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
    ↵↵
    -0.54
     
    -0.48
    (
    -0.48
    n
    -0.47
    dot
    -0.47
    .
    -0.47
     i
    -0.45
    松
    -0.45
     makan
    -0.43
    ,
    -0.43
    POSITIVE LOGITS
    ."));
    1.02
    '}>
    0.98
    "}>
    0.94
    ]");
    0.93
    >");
    0.92
     />);
    0.91
    }`}>
    0.90
     oprot
    0.90
    ']):
    0.90
    ("]");
    0.90
    Activations Density 0.003%

    No Known Activations