© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 561
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming syntax, particularly focusing on closing parentheses and related symbols

    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
    ing
    -0.63
    MatInputModule
    -0.62
    fang
    -0.60
    royd
    -0.59
     Farma
    -0.59
     bay
    -0.57
     Klo
    -0.57
     CHLOR
    -0.55
     hel
    -0.55
     Chrys
    -0.54
    POSITIVE LOGITS
    ])
    1.11
    **)
    1.06
    }))
    1.06
    ))
    1.03
    _))
    1.02
    __))
    1.01
    "")
    1.01
    ))
    1.00
    ]))
    1.00
     AssemblyVersion
    0.98
    Activations Density 1.193%

    No Known Activations