© 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. 20126
    Prev
    Next
    INDEX
    Explanations

    references to specific formatting or coding standards

    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
    GeneratedCode
    -0.78
    CodeAttribute
    -0.62
    sa
    -0.62
     sa
    -0.57
    ByExample
    -0.55
    TemporalType
    -0.54
    itanie
    -0.52
    ViewInit
    -0.50
     fo
    -0.49
    +#+#
    -0.49
    POSITIVE LOGITS
     Diſ
    1.14
     myſelf
    1.10
     Reſ
    1.02
     Monfieur
    1.02
     Eſ
    1.02
     deſt
    1.01
     Conſ
    0.99
     houſe
    0.98
     Houſe
    0.98
     purpoſe
    0.98
    Activations Density 0.037%

    No Known Activations