© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5640
    Prev
    Next
    INDEX
    Explanations

    the term "former" to identify past roles or positions held by individuals

    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
     Kull
    -0.70
     Marburg
    -0.68
     Angio
    -0.67
     Sien
    -0.67
    subsubsection
    -0.65
     Erle
    -0.64
    ạt
    -0.63
    IsContent
    -0.63
     Trish
    -0.62
     saites
    -0.62
    POSITIVE LOGITS
     former
    1.16
    Former
    1.12
     Former
    1.12
    former
    0.98
     ehemaligen
    0.96
     ehemalige
    0.95
     ex
    0.92
     Formerly
    0.75
    Formerly
    0.74
     Ex
    0.73
    Activations Density 0.020%

    No Known Activations