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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17450
    Prev
    Next
    INDEX
    Explanations

    references to employment and work-related 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
     nahilalakip
    -1.05
     متعلقه
    -0.89
    Rüyada
    -0.88
    utilisons
    -0.87
     تضيفلها
    -0.87
    DeleteBehavior
    -0.85
     initComponents
    -0.76
    hoeddwyd
    -0.75
    AccessorTable
    -0.73
     createSlice
    -0.71
    POSITIVE LOGITS
    druck
    0.48
    oka
    0.46
     defStyleAttr
    0.43
    rantes
    0.41
     đựng
    0.41
     présent
    0.39
    OKA
    0.39
    馈
    0.39
     Bassi
    0.39
     Alder
    0.38
    Activations Density 0.035%

    No Known Activations