© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1319
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating opposition or contradiction

    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
    311
    +0.09
    0.3%
    313
    +0.08
    0.2%
    411
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.02
    904
    +0.08
    0.02
    311
    +0.07
    0.02
    Negative Logits
    
    -0.82
    ⓧ
    -0.72
    <?
    -0.71
     faced
    -0.63
    JAKARTA
    -0.60
    endmodule
    -0.59
     essentially
    -0.56
    berater
    -0.53
    Mə
    -0.53
    Locatie
    -0.53
    POSITIVE LOGITS
     contrary
    2.14
     Contrary
    1.52
    contr
    1.36
    Contrary
    1.32
     lele
    1.28
     gend
    1.12
     contraire
    1.11
     zyn
    1.08
     idr
    1.07
     stik
    1.07
    Activations Density 0.210%

    No Known Activations