© 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. 10-RES-JB
    11. 1296
    Prev
    Next
    INDEX
    Explanations

    terms related to "barbarism" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1331
    +0.15
    0.9%
    1810
    +0.13
    0.8%
    680
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1331
    +0.15
    0.03
    1472
    +0.13
    0.02
    1507
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.16
    PerformLayout
    -0.68
    EndProject
    -0.61
     hit
    -0.60
    CreateIndex
    -0.60
     me
    -0.57
     fix
    -0.56
    مصادر
    -0.55
    RunWith
    -0.55
     Commission
    -0.54
    POSITIVE LOGITS
     maneu
    1.72
     ftu
    1.63
     unwarran
    1.62
     ftre
    1.59
     disagre
    1.58
     hcm
    1.58
     fep
    1.56
     emphat
    1.54
     perfon
    1.53
     depic
    1.53
    Activations Density 0.089%

    No Known Activations