© 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. 3357
    Prev
    Next
    INDEX
    Explanations

    references to agents in various 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
    Thur
    -0.76
     Quir
    -0.76
    prehension
    -0.71
    BIÉN
    -0.71
     Lockwood
    -0.70
    THS
    -0.69
     SWR
    -0.69
    conductivity
    -0.68
     Thur
    -0.68
     Krie
    -0.67
    POSITIVE LOGITS
     Agents
    1.98
     agents
    1.94
    Agents
    1.90
     Agent
    1.75
    agents
    1.74
     AGENTS
    1.73
     agent
    1.69
     AGENT
    1.67
    Agent
    1.66
    AGENT
    1.62
    Activations Density 0.089%

    No Known Activations