© 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. 24-RES-MATRYOSHKA-DC
    7. 764
    Prev
    Next
    INDEX
    Explanations

    phrases related to business relationships, planning, and consideration

    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.24.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.24.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
     dumne
    -0.64
     fatis
    -0.62
     cardia
    -0.61
    procedures
    -0.60
     PLW
    -0.59
    Становништво
    -0.59
    nappropriate
    -0.58
    InjectAttribute
    -0.58
     fubject
    -0.58
    ionales
    -0.57
    POSITIVE LOGITS
     startups
    1.16
     startup
    1.07
     tech
    1.06
     Startups
    0.94
     digital
    0.93
     fintech
    0.90
     Startup
    0.88
     founders
    0.88
     platform
    0.85
     disrupt
    0.84
    Activations Density 1.963%

    No Known Activations