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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1801
    Prev
    Next
    INDEX
    Explanations

    information related to yoga

    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
    58
    +0.07
    0.2%
    974
    +0.07
    0.2%
    492
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    974
    +0.07
    0.03
    981
    +0.07
    0.02
    762
    +0.07
    0.02
    Negative Logits
     continue
    -0.60
    
    -0.59
     maintain
    -0.58
     contend
    -0.57
     remain
    -0.57
     if
    -0.56
     be
    -0.55
    留
    -0.55
     proceed
    -0.54
     provide
    -0.54
    POSITIVE LOGITS
     YOGA
    1.97
    Yoga
    1.88
     yoga
    1.88
     Yoga
    1.83
    yoga
    1.79
     chèvre
    1.53
     fluo
    1.50
     fup
    1.47
     unce
    1.46
     squa
    1.46
    Activations Density 0.164%

    No Known Activations