© 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. 359
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and concepts related to research or studies

    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
    Hentet
    -0.81
    BeginInit
    -0.71
     initComponents
    -0.66
     }}(\
    -0.63
    ględ
    -0.61
    ]]:
    -0.57
    . 
    -0.57
     handleMessage
    -0.56
     hina
    -0.55
    ⇑
    -0.55
    POSITIVE LOGITS
     تانيه
    0.79
     delà
    0.69
     للمعارف
    0.66
     didalam
    0.64
    luß
    0.61
     Whilst
    0.59
    Whilst
    0.58
    の為
    0.55
     diatas
    0.55
    繋が
    0.55
    Activations Density 5.988%

    No Known Activations