© 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. 11335
    Prev
    Next
    INDEX
    Explanations

    references to entities and their relationships in a given context

    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
    photobucket
    -0.48
    原始内容存档于
    -0.47
    клопе
    -0.47
    rendon
    -0.47
    {
    -0.45
    preload
    -0.44
    Гі
    -0.43
    #
    -0.42
    {(\
    -0.42
    ]]=
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.64
     ejus
    0.59
    ắp
    0.58
    :✨
    0.57
    etheless
    0.57
     habet
    0.57
    HandlerContext
    0.56
     Swain
    0.56
     Phry
    0.56
     eorum
    0.54
    Activations Density 0.090%

    No Known Activations