© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3949
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical values or quantities

    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
    脚注の使い方
    -0.82
     StatefulWidget
    -0.80
    matics
    -0.77
    FormTagHelper
    -0.75
     lenker
    -0.73
    ArrowToggle
    -0.73
    makeText
    -0.73
     SIMBAD
    -0.72
     للمعارف
    -0.72
     CGSize
    -0.72
    POSITIVE LOGITS
     Romains
    0.58
     quæ
    0.57
     giapponese
    0.57
    galan
    0.52
     suivants
    0.52
     scolas
    0.52
     vocale
    0.50
     giapp
    0.49
     popolare
    0.49
     japonesa
    0.48
    Activations Density 0.082%

    No Known Activations