© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16474
    Prev
    Next
    INDEX
    Explanations

    code that handles user input and data processing in a programming environment

    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
    +#+#
    -0.74
    :✨
    -0.64
    -------
    -0.63
     ویکی‌پدی
    -0.59
    原始内容存档于
    -0.57
     AssemblyCulture
    -0.57
    sizeCache
    -0.57
     <=",
    -0.57
    +:+
    -0.56
     发表于
    -0.55
    POSITIVE LOGITS
     Measures
    0.49
     Mohawk
    0.49
    Interventions
    0.47
     Nausea
    0.47
     tartalomajánló
    0.46
    choline
    0.46
     Pleasure
    0.45
    äft
    0.45
    glDisable
    0.45
     newInstance
    0.45
    Activations Density 0.015%

    No Known Activations