© 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. 28339
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a central or crucial location within a narrative

    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
    WebControls
    -0.60
    ReusableCell
    -0.59
     mesmos
    -0.55
     tubercle
    -0.52
     concealer
    -0.52
    XmlAttribute
    -0.52
    jmniej
    -0.51
     Pues
    -0.50
     chèvre
    -0.50
    for
    -0.50
    POSITIVE LOGITS
     midst
    1.03
     amidst
    0.85
    amid
    0.78
     amid
    0.75
     Amid
    0.73
    MemoryWarning
    0.70
     surrounded
    0.69
    PLICATIONS
    0.68
    +:+
    0.68
    ruik
    0.67
    Activations Density 0.012%

    No Known Activations