© 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. 697
    Prev
    Next
    INDEX
    Explanations

    mentions of the term 'wrist'

    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
    1562
    +0.12
    0.4%
    442
    +0.11
    0.4%
    687
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.12
    0.06
    1896
    +0.11
    0.03
    1343
    +0.11
    0.05
    Negative Logits
    Tikang
    -0.75
    hamshire
    -0.60
    
    -0.59
    ruptedException
    -0.59
    żdy
    -0.57
     "..\..\..\
    -0.56
    дото
    -0.56
    ControllerAdvice
    -0.56
        
    -0.56
    </tbody>
    -0.55
    POSITIVE LOGITS
     accla
    1.42
     maneu
    1.40
     inev
    1.39
     reluct
    1.38
     increa
    1.37
     fuf
    1.35
     hcm
    1.32
     attemp
    1.30
     ricardo
    1.29
     fta
    1.29
    Activations Density 0.352%

    No Known Activations