© 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. 21621
    Prev
    Next
    INDEX
    Explanations

    instances of the opening curly brace character '{'

    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
    ArgsConstructor
    -0.72
     thiệu
    -0.69
     متعلقه
    -0.58
     endian
    -0.57
     ModelExpression
    -0.56
    ":[{
    -0.55
    lingua
    -0.55
    ="#"><
    -0.55
    {
    -0.55
     veille
    -0.54
    POSITIVE LOGITS
    ']}
    0.65
    ']?>
    0.63
    सन्दर्भ
    0.62
     transfieras
    0.62
    \}=\
    0.61
     &___
    0.60
    ophyllum
    0.59
    ssaint
    0.59
    }}}}
    0.59
    ']],
    0.59
    Activations Density 0.039%

    No Known Activations