© 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. 16445
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associated codes in data structures

    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
    ReusableCell
    -0.77
     препратки
    -0.70
    cshtml
    -0.69
     >=",
    -0.68
     resourceCulture
    -0.66
    XmlType
    -0.65
     <>",
    -0.64
    addContainerGap
    -0.63
    detectChanges
    -0.63
    تقاوى
    -0.60
    POSITIVE LOGITS
     dahin
    0.52
    مصادر
    0.49
     ossia
    0.49
     dementia
    0.48
    اقرأ
    0.48
     therefrom
    0.47
    antaranya
    0.47
    alleye
    0.46
     pylint
    0.46
     Slovensku
    0.46
    Activations Density 0.375%

    No Known Activations