© 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. 18-RES-MATRYOSHKA-DC
    7. 251
    Prev
    Next
    INDEX
    Explanations

    dialogue between characters, especially when posing a question or making a demand

    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.18.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.18.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
     daytime
    -0.75
     myſelf
    -0.68
     Италијани
    -0.68
    клопе
    -0.67
    contentLoaded
    -0.66
     itſelf
    -0.66
     nighttime
    -0.65
    aarrggbb
    -0.65
     CreateTagHelper
    -0.64
     deſt
    -0.64
    POSITIVE LOGITS
     grinned
    0.91
     smiled
    0.88
     chuckled
    0.85
     smirked
    0.82
     suddenly
    0.81
     nodded
    0.75
     smile
    0.75
     smir
    0.74
     chuckle
    0.73
     mumbled
    0.73
    Activations Density 1.220%

    No Known Activations