© 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. 874
    Prev
    Next
    INDEX
    Explanations

    phrases related to being named as defendants in a legal context

    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
    +0.09
    0.3%
    923
    +0.06
    0.2%
    1846
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    779
    +0.09
    0.03
    669
    +0.06
    0.03
    1846
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.13
    
    
    -0.97
    ⓧ
    -0.86
    <?
    -0.83
    /**
    -0.82
    /*
    -0.70
    lateinit
    -0.66
    <tfoot>
    -0.58
    Descripció
    -0.57
    Kontrola
    -0.57
    POSITIVE LOGITS
     maneu
    1.15
     maroc
    1.07
     wien
    0.99
     lamborghini
    0.99
     incess
    0.98
     Bibl
    0.97
     riva
    0.96
     viciss
    0.95
     drey
    0.93
     husqvarna
    0.92
    Activations Density 0.184%

    No Known Activations