© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 459
    Prev
    Next
    INDEX
    Explanations

    words related to profession, industries, studies, and organization

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    DockStyle
    -0.84
    脚注の使い方
    -0.70
    IsMutable
    -0.65
    duur
    -0.64
    IsContent
    -0.62
     judiciales
    -0.61
     noDo
    -0.60
    VersionUID
    -0.60
    engagent
    -0.59
     AssemblyCulture
    -0.59
    POSITIVE LOGITS
     industry
    0.94
     professionals
    0.71
     sector
    0.70
    industry
    0.69
     indust
    0.63
     Industry
    0.62
     services
    0.61
     mog
    0.61
     department
    0.60
     related
    0.60
    Activations Density 2.553%

    No Known Activations