© 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. 28401
    Prev
    Next
    INDEX
    Explanations

    terms related to medications and alcohol use disorder (AUD)

    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
    <eos>
    -0.47
     variés
    -0.46
     =
    -0.44
    @
    -0.44
     and
    -0.43
    ave
    -0.41
    ?
    -0.41
     but
    -0.41
    (
    -0.41
    ↵↵
    -0.40
    POSITIVE LOGITS
    invokeLater
    1.08
     Мексичка
    1.05
    IsMutable
    1.04
     propOrder
    0.93
    Personensuche
    0.91
     ویکی‌پدیا
    0.89
    AddTagHelper
    0.88
    +#+#
    0.87
     ***!
    0.84
    RectangleBorder
    0.84
    Activations Density 0.702%

    No Known Activations