© 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. 1187
    Prev
    Next
    INDEX
    Explanations

    terms related to events or locations, specifically those with a focus on health and civic engagement

    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
    1742
    +0.12
    0.4%
    1677
    +0.10
    0.3%
    1222
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.05
    1120
    +0.10
    0.04
    690
    +0.09
    0.04
    Negative Logits
     jaya
    -0.99
     hoga
    -0.89
     Muhamma
    -0.86
     bandung
    -0.85
     Karya
    -0.82
    izational
    -0.81
     Bekasi
    -0.78
     muna
    -0.77
     kayo
    -0.77
     Minang
    -0.77
    POSITIVE LOGITS
     Din
    1.82
    din
    1.82
    Din
    1.77
     din
    1.69
    DIN
    1.29
     DIN
    1.21
     Henderson
    1.19
    Henderson
    1.06
     Ante
    0.96
     Wang
    0.82
    Activations Density 0.309%

    No Known Activations