© 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. 31987
    Prev
    Next
    INDEX
    Explanations

    comparative symbols and conditions related to numerical evaluations

    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
    l
    -0.76
    </i>
    -0.73
    quad
    -0.72
    ’
    -0.72
    $
    -0.71
    <eos>
    -0.71
    ,”
    -0.70
    n
    -0.70
     “
    -0.69
    ”
    -0.68
    POSITIVE LOGITS
     myſelf
    1.45
     Efq
    1.38
     Theſe
    1.32
     themſelves
    1.27
    ^(@)
    1.24
     Jefus
    1.18
     himſelf
    1.17
    Lycka
    1.11
    ſelves
    1.09
     purpoſe
    1.09
    Activations Density 0.005%

    No Known Activations