© 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. 2532
    Prev
    Next
    INDEX
    Explanations

    the name "Kevin" and its variations in the text

    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
    795
    +0.18
    1.1%
    50
    +0.13
    0.8%
    1103
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    795
    +0.18
    0.03
    164
    +0.13
    0.02
    1194
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.21
    
    -0.72
    <?
    -0.69
    ⓧ
    -0.66
    /**
    -0.66
     endow
    -0.58
    AutoScaleMode
    -0.55
    writeFieldEnd
    -0.54
     endwhile
    -0.54
    <?
    -0.53
    POSITIVE LOGITS
     Kevin
    1.41
    Kevin
    1.35
     kevin
    1.34
    kevin
    1.09
     KEV
    1.09
     Banjar
    1.01
     Jambi
    0.91
     alban
    0.89
     pank
    0.88
     Ké
    0.88
    Activations Density 0.027%

    No Known Activations