© 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. 18729
    Prev
    Next
    INDEX
    Explanations

    references to healthcare professionals and their roles in advising or treating patients

    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
    uurs
    -0.48
     naman
    -0.44
     편
    -0.44
     
    -0.44
    urismo
    -0.43
    GenerationType
    -0.43
     sk
    -0.43
     sw
    -0.42
     over
    -0.41
     recruit
    -0.41
    POSITIVE LOGITS
    HostException
    0.89
     propOrder
    0.83
     незавершена
    0.81
    Попис
    0.80
     jsPsych
    0.69
     rospy
    0.68
     '\\;'
    0.68
     Roskov
    0.67
     Exacts
    0.65
    SharedCtor
    0.65
    Activations Density 0.087%

    No Known Activations