© 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. 2137
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and settlements

    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
    50
    +0.27
    1.0%
    1150
    +0.10
    0.4%
    297
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1371
    +0.27
    0.04
    1820
    +0.10
    0.03
    1815
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.67
     khiển
    -0.64
    ⓧ
    -0.63
    endif
    -0.61
    Parcelize
    -0.60
    InjectMocks
    -0.58
    octanol
    -0.58
    }{||
    -0.58
     Мексичка
    -0.57
    }],
    -0.56
    POSITIVE LOGITS
     Minang
    1.59
     maneu
    1.59
     disagre
    1.52
     shenan
    1.45
     stockholm
    1.44
     practition
    1.42
     milf
    1.41
     Juf
    1.40
     impra
    1.40
     bandung
    1.39
    Activations Density 0.370%

    No Known Activations