Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 23247
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data or references, particularly in scientific contexts

    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
    ็จ
    -0.48
     cui
    -0.44
     pic
    -0.43
     qu
    -0.43
     right
    -0.41
     ab
    -0.40
     material
    -0.40
     or
    -0.40
     for
    -0.39
    zA
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.97
    mybatisplus
    0.87
    BeginInit
    0.85
     useRouter
    0.84
    titleMargin
    0.81
     متعلقه
    0.80
     שוליים
    0.78
    __':
    
    0.77
     препратки
    0.77
     useStyles
    0.76
    Activations Density 0.019%

    No Known Activations