© 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. 17533
    Prev
    Next
    INDEX
    Explanations

    patterns in programming code or structured 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
    getWriter
    -0.82
     Pires
    -0.81
     aVar
    -0.79
     Humphries
    -0.78
    vetica
    -0.77
    Guido
    -0.75
     Bertram
    -0.74
     Hills
    -0.73
    Billie
    -0.73
     Metcalf
    -0.73
    POSITIVE LOGITS
                            
    1.53
    1.16
     Marcell
    0.90
     Gand
    0.82
    3
    0.82
    [][]
    0.81
     Margare
    0.79
     Pust
    0.79
     ―――――
    0.79
     Houſe
    0.78
    Activations Density 0.019%

    No Known Activations