© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 764
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of a 'lifetime commitment'

    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
    341
    +0.07
    0.2%
    900
    +0.06
    0.2%
    168
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1062
    +0.07
    0.03
    911
    +0.06
    0.03
    815
    +0.06
    0.02
    Negative Logits
    
    
    -0.74
    <?
    -0.72
    <?
    
    -0.70
    <!--
    
    -0.60
     ceded
    -0.56
    /**
    -0.56
     móg
    -0.54
    ///**
    -0.54
    //{
    
    -0.54
    //[
    -0.54
    POSITIVE LOGITS
     lifetime
    2.80
     Lifetime
    2.53
    lifetime
    2.39
    Lifetime
    2.30
     lifetimes
    2.14
     lifelong
    1.48
     LIF
    1.47
    LIF
    1.19
     lifespan
    1.09
     italia
    1.00
    Activations Density 0.153%

    No Known Activations