© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 857
    Prev
    Next
    INDEX
    Explanations

    phrases related to meeting or gathering events

    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
    390
    +0.12
    0.3%
    1705
    +0.10
    0.3%
    920
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.12
    0.05
    1343
    +0.10
    0.05
    184
    +0.08
    0.02
    Negative Logits
     teras
    -0.63
     makro
    -0.58
     panik
    -0.58
     akong
    -0.57
     kemer
    -0.57
     eksklu
    -0.55
     plastik
    -0.53
     geograf
    -0.52
     demokrat
    -0.52
     Poitiers
    -0.51
    POSITIVE LOGITS
    Meet
    1.11
     Meet
    0.91
     blackpink
    0.76
    MEET
    0.75
     seoul
    0.69
     Anton
    0.69
     beverly
    0.69
     doraemon
    0.66
    Anton
    0.65
     pixar
    0.65
    Activations Density 0.359%

    No Known Activations