© 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. 2548
    Prev
    Next
    INDEX
    Explanations

    HTML list structures and navigation elements

    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
    став
    -0.60
     Kira
    -0.57
    vori
    -0.57
     Joachim
    -0.57
     Cantor
    -0.56
    رف
    -0.55
    פיל
    -0.54
    annotation
    -0.54
     Kamin
    -0.54
    engertian
    -0.53
    POSITIVE LOGITS
    ul
    1.05
    bootstrapcdn
    0.90
    +:+
    0.85
    Datuak
    0.85
     onOptions
    0.82
     InputDecoration
    0.81
    UL
    0.79
    InvalidProtocol
    0.77
    Tazama
    0.77
    TargetException
    0.76
    Activations Density 0.017%

    No Known Activations