© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14371
    Prev
    Next
    INDEX
    Explanations

    phrases related to showcasing or displaying something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1910
    +0.11
    0.3%
    78
    +0.10
    0.3%
    678
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    869
    +0.11
    0.04
    851
    +0.10
    0.03
    78
    +0.10
    0.03
    Negative Logits
     maneu
    -1.04
     disagre
    -1.04
     apprehen
    -1.04
     milf
    -1.04
     tolerably
    -1.02
     shenan
    -1.00
     strick
    -0.99
     perfet
    -0.96
     unwarran
    -0.95
     reluct
    -0.94
    POSITIVE LOGITS
     show
    0.85
    show
    0.82
     showcase
    0.79
    Show
    0.78
     Show
    0.76
     demonstrate
    0.74
     shows
    0.73
     showing
    0.71
     showcases
    0.71
     showcasing
    0.69
    Activations Density 0.228%

    No Known Activations