© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30177
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or structures in text

    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
    sizeCache
    -0.82
    rrggbb
    -0.71
     nicio
    -0.64
     quelconque
    -0.63
    ValueStyle
    -0.63
     مرئيه
    -0.62
     semplici
    -0.61
    arranty
    -0.59
    
    -0.59
     يتيمه
    -0.59
    POSITIVE LOGITS
    HasForeignKey
    0.63
     Wayback
    0.57
    }{*}{
    0.56
    mybatisplus
    0.56
     surla
    0.56
     the
    0.53
     متعلقه
    0.52
    "],
    0.50
    льки
    0.47
    enschappe
    0.47
    Activations Density 0.073%

    No Known Activations