© 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. 9620
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to physics or advanced mathematics

    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
    ConstraintMaker
    -0.71
     eût
    -0.70
    
    -0.70
     ویکی‌پدی
    -0.68
    הערות
    -0.67
     gynnwys
    -0.66
     متعلقه
    -0.65
     виправивши
    -0.65
    migrationBuilder
    -0.64
    gól
    -0.63
    POSITIVE LOGITS
    Naissance
    0.60
    SourceChecksum
    0.57
     createSprite
    0.54
     ag
    0.52
    Slf
    0.52
     Angus
    0.52
     Ang
    0.52
    Nazionale
    0.52
    あり
    0.51
    entina
    0.50
    Activations Density 0.006%

    No Known Activations