© 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. 18-RES-MATRYOSHKA-DC
    7. 524
    Prev
    Next
    INDEX
    Explanations

    abbreviations, acronyms and initialisms related to software code or scientific data

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    ividual
    -0.62
    erapeutic
    -0.59
    orithms
    -0.57
     бе
    -0.57
    allerie
    -0.57
    azin
    -0.56
    BagConstraints
    -0.54
    jaer
    -0.52
    IPLE
    -0.49
    æus
    -0.49
    POSITIVE LOGITS
    ſelves
    1.07
     Theſe
    0.97
     Efq
    0.96
    ſelf
    0.95
     uſed
    0.90
     raiſ
    0.88
     myſelf
    0.88
     itſelf
    0.86
     ſeveral
    0.85
     purpoſe
    0.82
    Activations Density 0.930%

    No Known Activations