© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    phrases related to weight loss supplements and intake procedures

    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
    411
    +0.11
    0.4%
    67
    +0.10
    0.3%
    1178
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.11
    0.03
    1120
    +0.10
    0.04
    1343
    +0.08
    0.04
    Negative Logits
    <?
    -0.69
    
    -0.60
    Giao
    -0.58
    dis
    -0.54
     activate
    -0.54
    롯
    -0.54
    ьи
    -0.53
     operate
    -0.53
    private
    -0.53
    /*
    -0.53
    POSITIVE LOGITS
     catég
    1.21
     dévou
    1.20
     oleo
    1.15
     tamen
    1.14
     impra
    1.14
     habile
    1.14
     nutella
    1.13
     sappi
    1.12
     ecru
    1.11
     unden
    1.11
    Activations Density 0.301%

    No Known Activations