© 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. 19544
    Prev
    Next
    INDEX
    Explanations

    references to employers and employment-related topics

    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
    稲田
    -0.77
     in
    -0.61
     ‘
    -0.60
     
    -0.60
     consultato
    -0.58
     Kaye
    -0.56
    __["
    -0.56
    жек
    -0.56
     mem
    -0.55
     fu
    -0.55
    POSITIVE LOGITS
     Employers
    1.41
    Employers
    1.40
     employers
    1.30
     Employer
    1.23
    Employer
    1.16
     employer
    1.11
     Efq
    0.98
     Monfieur
    0.97
    employer
    0.96
     Majefty
    0.96
    Activations Density 0.005%

    No Known Activations