© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5878
    Prev
    Next
    INDEX
    Explanations

    terms related to financial balance or equilibrium

    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
    1573
    +0.13
    0.4%
    75
    +0.11
    0.4%
    1331
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.13
    0.03
    75
    +0.11
    0.02
    642
    +0.10
    0.02
    Negative Logits
     encomp
    -1.01
     Epif
    -0.95
     increa
    -0.89
    ,¹
    -0.89
     Simult
    -0.89
     indestru
    -0.87
     reluct
    -0.87
     simplif
    -0.86
     unlaw
    -0.86
     inext
    -0.85
    POSITIVE LOGITS
     balance
    1.45
    balance
    1.34
     Balance
    1.31
     balances
    1.28
    Balance
    1.26
     balanced
    1.23
    balanced
    1.20
     balancing
    1.19
    balances
    1.14
    balancing
    1.13
    Activations Density 0.073%

    No Known Activations