© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30449
    Prev
    Next
    INDEX
    Explanations

    references to maternal factors and conditions

    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
    脚注の使い方
    -0.67
     Pli
    -0.65
    pyplot
    -0.64
     Alvar
    -0.63
     Vind
    -0.62
     Pizarro
    -0.60
    hilangan
    -0.57
     Muck
    -0.57
     Hoover
    -0.57
     Mocking
    -0.57
    POSITIVE LOGITS
     Maternal
    1.00
     maternal
    0.94
    Mater
    0.86
    UIControlState
    0.83
    matern
    0.82
    msgs
    0.74
     Cardoso
    0.73
    あります
    0.70
    iencies
    0.70
     Matheson
    0.69
    Activations Density 0.003%

    No Known Activations