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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5638
    Prev
    Next
    INDEX
    Explanations

    escape sequences or special characters used in programming syntax

    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
     Treff
    -0.72
    RTGC
    -0.66
     Kości
    -0.65
     Amalia
    -0.64
    Izvori
    -0.63
     cruzado
    -0.63
     noires
    -0.63
    +#+#
    -0.62
    rosz
    -0.61
    Burst
    -0.61
    POSITIVE LOGITS
    TagHelper
    0.61
    alpin
    0.61
    PathVariable
    0.61
     ostavi
    0.61
     railway
    0.58
    NegativeButton
    0.57
    chkin
    0.57
    }\]
    0.57
    BeforeAll
    0.57
    IPAC
    0.57
    Activations Density 0.210%

    No Known Activations