© 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. 847
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or location named "Cruz"

    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
    313
    +0.12
    0.3%
    1331
    +0.09
    0.3%
    1272
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.12
    0.01
    1343
    +0.09
    0.04
    1363
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.88
     xdrive
    -0.87
     lamborghini
    -0.87
     reluct
    -0.86
     dci
    -0.83
     outlander
    -0.83
     mitsubishi
    -0.82
    timately
    -0.82
     gti
    -0.82
     sportback
    -0.82
    POSITIVE LOGITS
     Cruz
    1.92
    Cruz
    1.60
     CRUZ
    1.12
    cruz
    1.01
    ilt
    0.97
     cruz
    0.96
    acky
    0.74
     Cult
    0.68
     cult
    0.65
    RenderAtEndOf
    0.64
    Activations Density 0.274%

    No Known Activations