© 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. 16460
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical operations and expressions

    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
    Viitteet
    -0.82
     initComponents
    -0.73
     StatefulWidget
    -0.72
    SequentialGroup
    -0.69
    herself
    -0.68
    Czytaj
    -0.66
    StoryboardSegue
    -0.66
     فريبيس
    -0.65
     كومونز
    -0.63
    XmlEnum
    -0.63
    POSITIVE LOGITS
    ])):
    0.48
     also
    0.47
     off
    0.45
    Vanjske
    0.44
     PopupWindow
    0.43
     <=",
    0.43
     tartış
    0.43
    жидан
    0.43
     reg
    0.42
    oubliez
    0.42
    Activations Density 0.011%

    No Known Activations