© 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. 977
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal concepts and regulations

    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
    501
    +0.10
    0.3%
    390
    +0.08
    0.2%
    1127
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.02
    501
    +0.08
    0.02
    184
    +0.08
    0.01
    Negative Logits
     ineffec
    -0.77
     nursed
    -0.74
     underval
    -0.74
     subgoals
    -0.72
     unspeak
    -0.71
     endeav
    -0.69
     endeavouring
    -0.69
     vainly
    -0.68
     shivered
    -0.67
     roused
    -0.66
    POSITIVE LOGITS
    ality
    2.60
    alities
    1.92
    ALITY
    1.78
    uality
    0.91
    alité
    0.84
    lity
    0.72
    alised
    0.71
     gesta
    0.67
    alty
    0.67
    Personensuche
    0.66
    Activations Density 0.205%

    No Known Activations