© 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. 32620
    Prev
    Next
    INDEX
    Explanations

    references to the term "Mad" in various 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
    ValueStyle
    -0.85
     propOrder
    -0.85
     Juris
    -0.83
    IsContent
    -0.80
     layui
    -0.78
    Juris
    -0.76
    afone
    -0.74
     Buckley
    -0.73
    Tazama
    -0.71
    ffl
    -0.71
    POSITIVE LOGITS
     Mad
    1.71
    Mad
    1.66
     MAD
    1.52
     mad
    1.51
    MAD
    1.30
     Madsen
    1.21
    mad
    1.19
     Maddox
    1.14
     Maddie
    1.09
     Madera
    1.03
    Activations Density 0.021%

    No Known Activations