© 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. 2997
    Prev
    Next
    INDEX
    Explanations

    contextual references to characters or events in narratives

    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
     Archiproducts
    -0.79
    ChildScrollView
    -0.76
    makeConstraints
    -0.75
     nahilalakip
    -0.70
     surla
    -0.69
    Personendaten
    -0.68
     arşivlendi
    -0.63
     Superhosts
    -0.63
    SharedDtor
    -0.62
    complexType
    -0.59
    POSITIVE LOGITS
     distanciation
    0.52
     Protección
    0.50
    personen
    0.50
    Kaieteur
    0.49
    mesg
    0.47
    atschappij
    0.47
    DNEY
    0.46
     --
    0.46
    viere
    0.45
    CodeAttribute
    0.44
    Activations Density 2.273%

    No Known Activations