© 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. 32430
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to anti-therapies or anti-drug responses in medical contexts

    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
     дописавши
    -0.88
    EDEFAULT
    -0.85
    Clik
    -0.80
    .';
    -0.74
     ſind
    -0.72
    })->
    -0.71
    
    -0.70
    archiviato
    -0.69
    .";
    -0.69
    \}\\
    -0.69
    POSITIVE LOGITS
     people
    0.56
    rektor
    0.54
    ism
    0.54
    oro
    0.53
    yolo
    0.53
    nya
    0.52
     whole
    0.52
    ดย
    0.52
    WithMany
    0.52
     Ce
    0.51
    Activations Density 0.008%

    No Known Activations