© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 202
    Prev
    Next
    INDEX
    Explanations

    terms related to clothing and fashion trends

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1045
    +0.10
    0.3%
    1328
    +0.08
    0.2%
    68
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.10
    0.03
    12
    +0.08
    0.02
    1218
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.03
    gov
    -0.72
    uesia
    -0.68
    </tbody>
    -0.65
    docs
    -0.62
    HideFlags
    -0.61
    후
    -0.61
     raise
    -0.61
     بتاريخ
    -0.60
    ,
    -0.60
    POSITIVE LOGITS
     closet
    2.01
     Closet
    1.84
    closet
    1.78
     closets
    1.72
     stockholm
    1.68
     sappi
    1.56
     lidl
    1.56
     affor
    1.55
     wien
    1.54
     maneu
    1.54
    Activations Density 0.138%

    No Known Activations