© 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. 23742
    Prev
    Next
    INDEX
    Explanations

    references to figures in technical documents

    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
     StatefulWidget
    -0.59
    kloped
    -0.59
    parsedMessage
    -0.58
     Peterson
    -0.53
     @"/
    -0.53
     SqlParameter
    -0.51
     fallu
    -0.50
    himo
    -0.50
     Drapeau
    -0.50
     remplacé
    -0.49
    POSITIVE LOGITS
    noStroke
    0.69
     Waray
    0.66
    sizeCache
    0.64
    ViewInit
    0.60
    Revenir
    0.57
    ftagPool
    0.57
     anzi
    0.56
    AnimationFrame
    0.56
    evich
    0.55
    leurs
    0.54
    Activations Density 0.001%

    No Known Activations