© 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. 25467
    Prev
    Next
    INDEX
    Explanations

    specific optical and wellness-related businesses and services

    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
     Monfieur
    -0.84
     myſelf
    -0.83
     itſelf
    -0.81
     Efq
    -0.79
     houſe
    -0.77
     Houſe
    -0.77
     themſelves
    -0.72
     purpoſe
    -0.72
     againſt
    -0.69
     Theſe
    -0.69
    POSITIVE LOGITS
    قایناقلار
    0.61
    webElementGuid
    0.60
    AddWithValue
    0.53
     >=",
    0.51
    ьа
    0.47
     &
    0.47
     ͜ʖ
    0.45
    님
    0.44
     :=
    0.44
    toJSONString
    0.44
    Activations Density 0.071%

    No Known Activations