© 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. 2434
    Prev
    Next
    INDEX
    Explanations

    negations or words that imply contradiction

    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
    +0.29
    1.1%
    1262
    +0.13
    0.5%
    1044
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1262
    +0.29
    0.11
    950
    +0.13
    0.10
    1974
    +0.10
    0.08
    Negative Logits
    <bos>
    -2.75
    Аб
    -0.58
     дописавши
    -0.57
    ⓧ
    -0.56
    GEBURTSDATUM
    -0.50
     join
    -0.50
     Table
    -0.49
     IActionResult
    -0.49
     Pacific
    -0.48
    Портали
    -0.48
    POSITIVE LOGITS
     vectra
    1.13
     lidl
    1.11
    ">/
    1.06
    capulco
    1.03
     jetta
    1.03
    postolic
    1.03
    ">...
    1.03
     unlaw
    1.02
     burberry
    1.01
     starbucks
    1.01
    Activations Density 0.310%

    No Known Activations