© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12281
    Prev
    Next
    INDEX
    Explanations

    phrases related to the country Vietnam and associated topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    390
    +0.14
    0.5%
    1334
    +0.13
    0.4%
    687
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.14
    0.02
    860
    +0.13
    0.02
    405
    +0.10
    0.01
    Negative Logits
     thuy
    -1.06
     tuong
    -0.91
     khong
    -0.69
     nguoi
    -0.68
     tanya
    -0.68
     luy
    -0.67
    Nguy
    -0.66
     nguyễn
    -0.64
     giu
    -0.64
     chuy
    -0.63
    POSITIVE LOGITS
     Vietnam
    1.35
    Vietnam
    1.28
     Vietnamese
    1.16
    Vietnamese
    0.99
    vietnam
    0.91
     Nguyen
    0.85
     vietnam
    0.82
     Viet
    0.81
     Saigon
    0.73
     Hanoi
    0.71
    Activations Density 0.061%

    No Known Activations