© 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. 26631
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions, particularly those related to transformations and functions in a quantum or theoretical physics context

    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
    ValueStyle
    -0.62
     חיצוניים
    -0.60
     برانيه
    -0.58
    abestanden
    -0.55
     surla
    -0.55
    onoi
    -0.54
    brigens
    -0.52
     légale
    -0.52
     Spisak
    -0.51
    writeField
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.60
     prioritise
    0.57
    يميديا
    0.53
    plish
    0.49
     prioritize
    0.48
    LAHOMA
    0.47
    flexGrow
    0.45
    intios
    0.45
    localctx
    0.45
    urate
    0.45
    Activations Density 0.175%

    No Known Activations