© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 352
    Prev
    Next
    INDEX
    Explanations

    references to the Twilight series and related terms

    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
    1045
    +0.09
    0.3%
    50
    +0.07
    0.2%
    528
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.09
    0.01
    1343
    +0.07
    0.04
    1935
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.24
    /***
    -1.00
     intersper
    -0.79
     milf
    -0.78
     disgra
    -0.78
     embra
    -0.77
     outlander
    -0.76
     shenan
    -0.75
     benevol
    -0.75
     encomp
    -0.74
    POSITIVE LOGITS
     Levin
    0.95
     Twilight
    0.86
    Twilight
    0.83
     Zion
    0.76
     sovereignty
    0.72
     electoral
    0.71
     Electoral
    0.66
     cyber
    0.66
    Zion
    0.64
     twilight
    0.63
    Activations Density 0.263%

    No Known Activations