© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23513
    Prev
    Next
    INDEX
    Explanations

    references to dialog-related terms and components

    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
    Negative Logits
    Datuak
    -0.81
    存于互联网档案馆
    -0.77
     تضيفلها
    -0.68
     Bezirks
    -0.64
    EDER
    -0.62
     wealth
    -0.62
    ความ
    -0.62
    Tener
    -0.62
    +#+#
    -0.61
    ########.
    -0.61
    POSITIVE LOGITS
     MatDialog
    1.48
     Dialog
    1.33
     dialog
    1.30
     DIALOG
    1.26
    dialog
    1.23
    DIALOG
    1.23
    Dialog
    1.02
     Dialogue
    0.99
    Dialogs
    0.94
     dialogue
    0.89
    Activations Density 0.004%

    No Known Activations