© 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. 26464
    Prev
    Next
    INDEX
    Explanations

    terms related to software assembly attributes and licensing information

    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
     للمعارف
    -0.60
    GEBURTS
    -0.54
     FetchType
    -0.52
    genöss
    -0.49
    toupper
    -0.49
     SafeMath
    -0.48
    stridium
    -0.47
    posia
    -0.47
     selection
    -0.46
     actionPerformed
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.93
    IGraphics
    0.56
     الرياضيه
    0.55
    rawDesc
    0.55
    twimg
    0.55
     setError
    0.54
    !***
    0.54
     Paglinawan
    0.53
    
    0.53
    AccessorTable
    0.52
    Activations Density 0.005%

    No Known Activations