© 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. 25043
    Prev
    Next
    INDEX
    Explanations

    the term "abs" which likely relates to absolute measurements or concepts in a scientific 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
    Negative Logits
     }}"></
    -0.77
     jspb
    -0.77
    ="'+
    -0.73
    reiz
    -0.69
    RenderAtEndOf
    -0.67
     pestaña
    -0.63
    ungkinkan
    -0.60
     alvor
    -0.59
     Reyna
    -0.59
    ])/
    -0.59
    POSITIVE LOGITS
     abs
    1.46
    abs
    1.40
     Abs
    1.40
     ABS
    1.40
    Abs
    1.28
    ABS
    1.23
     Zamora
    0.90
     Wolfsburg
    0.90
     splint
    0.88
     abscess
    0.83
    Activations Density 0.003%

    No Known Activations