© 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. 5386
    Prev
    Next
    INDEX
    Explanations

    phrases indicating user questions or requests related to programming or technical problems

    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
    AdapterView
    -0.53
    得上
    -0.46
    Millions
    -0.45
    weiss
    -0.44
     sch
    -0.43
    bulo
    -0.43
     millions
    -0.43
    Hentet
    -0.43
    lijkheid
    -0.42
     Benson
    -0.42
    POSITIVE LOGITS
    InjectAttribute
    1.05
    ſelf
    0.85
    RTLR
    0.84
     незавершена
    0.81
    ſelves
    0.76
    EndContext
    0.73
     Савезне
    0.73
    bibitem
    0.72
     发表于
    0.71
    hObject
    0.70
    Activations Density 0.343%

    No Known Activations