© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32462
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to structured data or mathematical contexts

    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
    Negative Logits
    NOPQRST
    -0.82
     InputDecoration
    -0.80
     المعيارى
    -0.79
    antMatchers
    -0.78
    OGND
    -0.77
    TestBed
    -0.76
    providedIn
    -0.76
    évaluateur
    -0.75
    MLLoader
    -0.74
    expandindo
    -0.73
    POSITIVE LOGITS
     list
    0.52
     szerző
    0.45
    rain
    0.44
     kuin
    0.44
     lijst
    0.43
     énon
    0.42
     червня
    0.41
    wellen
    0.41
    ui
    0.41
     besk
    0.41
    Activations Density 0.122%

    No Known Activations