© 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. 19439
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis and metrics in research contexts

    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
    httphttps
    -0.83
    __(/*!
    -0.75
    tvguidetime
    -0.73
     للمعارف
    -0.72
     فريبيس
    -0.72
     fallu
    -0.71
    脚注の使い方
    -0.71
     Normdatei
    -0.68
     Jinping
    -0.66
    SourceChecksum
    -0.66
    POSITIVE LOGITS
    LayoutInflater
    0.45
    unga
    0.45
     trách
    0.44
    รง
    0.42
     Where
    0.41
    AuthProvider
    0.41
    BuilderFactory
    0.41
     medel
    0.41
     thác
    0.41
    重
    0.39
    Activations Density 0.217%

    No Known Activations