© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 263
    Prev
    Next
    INDEX
    Explanations

    references to concerns or issues regarding societal topics and discussions

    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
    abre
    -0.57
     lini
    -0.57
    ણ
    -0.56
     original
    -0.56
     réussi
    -0.55
     full
    -0.54
     sede
    -0.54
    Original
    -0.54
     reçu
    -0.53
     placé
    -0.52
    POSITIVE LOGITS
     about
    1.22
     متعلقه
    1.16
     abt
    1.16
     matters
    1.13
     Tentang
    1.13
     Acerca
    1.13
    about
    1.09
     About
    1.07
     ABOUT
    1.07
    ABOUT
    1.05
    Activations Density 1.884%

    No Known Activations