© 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. 21787
    Prev
    Next
    INDEX
    Explanations

    terms related to errors and invalid inputs

    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
    endpush
    -0.78
     LIRE
    -0.73
    createCanvas
    -0.73
    ViewFeatures
    -0.72
    othermic
    -0.69
     Galile
    -0.69
    writeFieldEnd
    -0.69
     JTable
    -0.68
     يتيمه
    -0.67
     ويكيميديا
    -0.67
    POSITIVE LOGITS
    чня
    0.56
    InvalidProtocol
    0.56
    śla
    0.52
     dzi
    0.49
    apad
    0.48
     Cranston
    0.48
    لاح
    0.48
    enschaft
    0.47
    ksan
    0.47
     Bristol
    0.47
    Activations Density 0.009%

    No Known Activations