© 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. 2247
    Prev
    Next
    INDEX
    Explanations

    phrases that imply conditionality or define relationships

    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
     estimés
    -0.62
     uſed
    -0.61
     myſelf
    -0.56
     Theſe
    -0.54
     dieux
    -0.54
     izvē
    -0.52
     pleaſure
    -0.52
     neceſſ
    -0.50
    how
    -0.50
     Boven
    -0.50
    POSITIVE LOGITS
     ComVisible
    0.88
    ThroughAttribute
    0.81
    +#+#
    0.80
    Personensuche
    0.75
    InteropServices
    0.74
     propOrder
    0.71
     typelib
    0.71
    IndentedString
    0.71
    Expan
    0.68
    makeText
    0.68
    Activations Density 0.050%

    No Known Activations