© 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. 14696
    Prev
    Next
    INDEX
    Explanations

    references to medical standards of care

    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
     press
    -0.55
     Press
    -0.49
    /
    -0.48
     (
    -0.46
     et
    -0.45
     si
    -0.45
     
    -0.45
    am
    -0.45
     u
    -0.45
    ,
    -0.44
    POSITIVE LOGITS
     themſelves
    1.09
     himſelf
    1.06
     purpoſe
    1.05
    MigrationBuilder
    1.03
     houſe
    1.02
     itſelf
    1.02
     Monfieur
    1.00
     myſelf
    0.97
     pleaſure
    0.94
     becauſe
    0.94
    Activations Density 0.031%

    No Known Activations