© 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. 22762
    Prev
    Next
    INDEX
    Explanations

    phrases or structures relating to mathematical expressions or derivatives

    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
    resizingMask
    -0.60
     BoxFit
    -0.58
    titial
    -0.53
     domestiques
    -0.50
     修
    -0.49
    nologue
    -0.47
    getLog
    -0.47
    Looper
    -0.46
     duża
    -0.46
    chief
    -0.46
    POSITIVE LOGITS
    SourceChecksum
    0.70
     EconPapers
    0.68
    fjspx
    0.68
    GEBURTSDATUM
    0.66
     désolés
    0.65
     autorytatywna
    0.62
     referenties
    0.62
     مُعرِّف
    0.59
    lances
    0.59
    مصادر
    0.58
    Activations Density 0.008%

    No Known Activations