© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 878
    Prev
    Next
    INDEX
    Explanations

    mentions of economic systems, particularly capitalism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1491
    +0.10
    0.3%
    1145
    +0.09
    0.3%
    645
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.04
    1896
    +0.09
    0.03
    1120
    +0.09
    0.04
    Negative Logits
    Enllaços
    -0.62
    spesies
    -0.60
     gede
    -0.58
    glie
    -0.56
    diplom
    -0.54
     защото
    -0.54
    Kjelder
    -0.54
     bedien
    -0.53
     stoff
    -0.53
    mmap
    -0.53
    POSITIVE LOGITS
     capitalism
    1.19
     austerity
    1.16
     bandung
    1.12
     capitalist
    1.11
     Capitalism
    1.11
     fucker
    1.11
     peppa
    1.08
     lmfao
    1.07
     sequestration
    1.05
     seques
    1.04
    Activations Density 0.365%

    No Known Activations