Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 29666
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to alcohol use disorder and its treatments

    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
    etheless
    -1.16
    mybatisplus
    -0.93
    Cuánt
    -0.90
    SharedCtor
    -0.86
     crutches
    -0.84
    queryInterface
    -0.81
    IsMutable
    -0.81
    :✨
    -0.80
    ✨:
    -0.80
    — 
    -0.79
    POSITIVE LOGITS
    a
    1.02
    rou
    0.79
    エイ
    0.75
    strick
    0.75
    sing
    0.73
    lis
    0.70
    ree
    0.68
    lig
    0.67
    τά
    0.66
    iras
    0.66
    Activations Density 0.182%

    No Known Activations