© 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. 10-RES-JB
    11. 2529
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare costs and payment methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1842
    +0.27
    1.2%
    50
    +0.23
    1.1%
    394
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.27
    0.09
    908
    +0.23
    0.06
    184
    +0.16
    0.01
    Negative Logits
    <bos>
    -2.47
     intersper
    -1.91
     shenan
    -1.77
     encomp
    -1.45
     unspeak
    -1.39
     reluct
    -1.35
     pamph
    -1.34
     philanth
    -1.33
     disreg
    -1.33
     impra
    -1.31
    POSITIVE LOGITS
     strategia
    0.79
    RectangleBorder
    0.78
    󠁢
    0.77
     riva
    0.75
     masaj
    0.73
     Gnaden
    0.71
     noten
    0.71
     sfera
    0.71
     Weisheit
    0.71
     tappa
    0.69
    Activations Density 2.339%

    No Known Activations