© 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. 1080
    Prev
    Next
    INDEX
    Explanations

    locations, specifically "Nash" or "Nashua" in different contexts

    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
    596
    +0.09
    0.3%
    1053
    +0.09
    0.3%
    341
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.09
    0.03
    690
    +0.09
    0.03
    1343
    +0.09
    0.03
    Negative Logits
    exitRule
    -0.74
    wikidata
    -0.71
     poll
    -0.70
    +:+
    -0.69
    पया
    -0.68
    Javadoc
    -0.68
    énario
    -0.67
    poll
    -0.67
    <bos>
    -0.67
    BASEPATH
    -0.67
    POSITIVE LOGITS
     nash
    2.25
     Nash
    2.21
     shenan
    2.05
     reluct
    2.05
    Nash
    2.00
     ricardo
    1.93
     sergio
    1.92
     maneu
    1.88
     strick
    1.87
     felipe
    1.84
    Activations Density 0.236%

    No Known Activations