© 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. 23720
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Andrew."

    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
     Pele
    -0.87
    Pele
    -0.86
     FSC
    -0.84
    FilterChain
    -0.82
     jis
    -0.81
     hés
    -0.79
    tvguidetime
    -0.78
     okuyayım
    -0.75
     Habit
    -0.75
    Jis
    -0.75
    POSITIVE LOGITS
     Andrew
    1.38
    ANDREW
    1.20
    Andrew
    1.18
     ANDREW
    1.13
     andrew
    1.13
     Andrews
    1.06
    Andrews
    0.99
    andrew
    0.94
     Drew
    0.75
    es
    0.75
    Activations Density 0.005%

    No Known Activations