© 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. 2388
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Clint."

    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
    900
    +0.18
    0.9%
    161
    +0.15
    0.8%
    528
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.04
    1741
    +0.15
    0.00
    1056
    +0.15
    0.03
    Negative Logits
     shenan
    -0.93
     unve
    -0.91
     encomp
    -0.89
     unlaw
    -0.89
     snoopy
    -0.89
     intersper
    -0.86
     Incenti
    -0.86
     gaily
    -0.85
     impractica
    -0.85
     disreg
    -0.82
    POSITIVE LOGITS
    Clint
    1.01
     Clint
    0.98
     Homeland
    0.87
     uovo
    0.78
     pilar
    0.78
     merid
    0.78
     Palest
    0.77
     frans
    0.76
     lomb
    0.76
     monit
    0.75
    Activations Density 0.226%

    No Known Activations