© 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. 834
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically mentioning years ago

    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
    +0.14
    0.7%
    1438
    +0.04
    0.2%
    2034
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.14
    0.06
    1650
    +0.04
    0.05
    1628
    +0.04
    0.05
    Negative Logits
    <bos>
    -1.76
    public
    -0.80
    ///**
    -0.73
    const
    -0.70
     add
    -0.67
     serve
    -0.67
     manage
    -0.67
     maintain
    -0.66
     promote
    -0.66
     continue
    -0.66
    POSITIVE LOGITS
     affor
    2.16
     maneu
    2.16
     increa
    1.96
     impra
    1.86
     stockholm
    1.85
     madonna
    1.84
     milf
    1.84
     guarante
    1.84
     disagre
    1.83
     eiffel
    1.82
    Activations Density 0.066%

    No Known Activations