© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11463
    Prev
    Next
    INDEX
    Explanations

    phrases associated with cause and effect relationships in discussions

    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
    DllImport
    -0.69
     pylint
    -0.64
     Eſ
    -0.63
     تانيه
    -0.62
    ourite
    -0.60
     seru
    -0.59
     يتيمه
    -0.59
     PROGRESS
    -0.58
    وزيع
    -0.56
     ſer
    -0.56
    POSITIVE LOGITS
    GoogleApiClient
    0.57
    thias
    0.56
    mobileqq
    0.55
    barang
    0.53
    brainly
    0.53
     having
    0.52
     adott
    0.51
    fxml
    0.50
    }>
    0.50
     Orrell
    0.49
    Activations Density 0.059%

    No Known Activations