© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    email communication related terms

    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
    50
    +0.21
    1.2%
    2019
    +0.06
    0.3%
    1842
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.21
    -0.08
    1419
    +0.06
    -0.01
    50
    +0.05
    0.21
    Negative Logits
    <bos>
    -3.84
    
    -1.26
    ⓧ
    -1.25
    /**
    -1.23
    <?
    -1.12
    /*
    -1.03
    /***
    -0.99
    <?
    -0.91
    /*++
    -0.86
     springfox
    -0.76
    POSITIVE LOGITS
     maroc
    0.96
     ananas
    0.83
     balkon
    0.81
     galeria
    0.79
     ados
    0.75
     marte
    0.74
     benzin
    0.74
     silikon
    0.73
     maske
    0.73
     klap
    0.73
    Activations Density 6.413%

    No Known Activations