© 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. 10842
    Prev
    Next
    INDEX
    Explanations

    terms related to technical analysis and medical procedures

    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
     للمعارف
    -0.88
     Савезне
    -0.77
     EconPapers
    -0.75
    Datuak
    -0.74
     يتيمه
    -0.68
    styleType
    -0.66
     autorytatywna
    -0.66
    GraphicsUnit
    -0.65
    Бахар
    -0.65
     gyhoeddwyd
    -0.65
    POSITIVE LOGITS
     normal
    0.60
    Normal
    0.56
    normal
    0.56
    NORMAL
    0.55
     normale
    0.54
    正常
    0.51
     ordinaria
    0.51
     ordinary
    0.50
     NORMAL
    0.49
     zwyk
    0.49
    Activations Density 0.303%

    No Known Activations