© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19625
    Prev
    Next
    INDEX
    Explanations

    references to time periods, particularly those related to the mid-20th century

    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
    ']")
    -0.87
    олові
    -0.85
    %)$
    -0.79
    )$}
    -0.77
    InputBorder
    -0.77
    >")
    -0.77
     Feldman
    -0.75
    }_\
    -0.73
     центре
    -0.73
    }')
    -0.73
    POSITIVE LOGITS
    Mid
    1.08
     MID
    1.08
     midwives
    1.02
     Mid
    1.01
    MID
    0.96
    mid
    0.95
     mid
    0.94
     midterm
    0.83
     midwife
    0.82
     Middlesex
    0.81
    Activations Density 0.016%

    No Known Activations