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. 25564
    Prev
    Next
    INDEX
    Explanations

    the presence of the abbreviation "BD" in various 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
    Not in Any Lists

    No Comments

    Negative Logits
     Kuk
    -0.80
     Gerry
    -0.73
     Arrondissement
    -0.73
     Etter
    -0.70
    ความ
    -0.69
     kuk
    -0.69
    Kuk
    -0.69
     Gren
    -0.69
     alky
    -0.68
    GRAN
    -0.67
    POSITIVE LOGITS
     BD
    1.44
    BD
    1.28
     bd
    1.16
    xbd
    1.02
    bd
    0.96
     Cheney
    0.94
     initComponents
    0.85
    piecz
    0.79
     ABD
    0.78
    BDL
    0.77
    Activations Density 0.026%

    No Known Activations