© 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. 26801
    Prev
    Next
    INDEX
    Explanations

    references to time periods or historical 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
     oprot
    -0.83
    MLLoader
    -0.79
     disambiguazione
    -0.72
     Baillargeon
    -0.70
    ItemBackground
    -0.70
    lottesville
    -0.69
     AssemblyCulture
    -0.68
    FXML
    -0.67
    rainian
    -0.67
    RuleContext
    -0.64
    POSITIVE LOGITS
    ดด
    0.45
     gra
    0.45
    eren
    0.42
     special
    0.41
    Viitteet
    0.41
    ("}\
    0.41
    chach
    0.40
     tudo
    0.40
     haver
    0.39
    lwjgl
    0.39
    Activations Density 0.209%

    No Known Activations