© 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. 8471
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly in the context of programming or data representation

    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
    featureID
    -0.63
    ValueStyle
    -0.60
    iempos
    -0.57
    رشف
    -0.56
    acry
    -0.56
     nahilalakip
    -0.56
     Chriftian
    -0.55
     archivi
    -0.53
     متعلقه
    -0.53
    ToBounds
    -0.52
    POSITIVE LOGITS
    abetes
    0.54
    ản
    0.52
    makeText
    0.52
     propTypes
    0.50
     AppBar
    0.49
     tâche
    0.48
     cero
    0.48
    styleType
    0.47
    requireNonNull
    0.47
    owulf
    0.47
    Activations Density 0.115%

    No Known Activations