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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13710
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to Donald Trump

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1741
    +0.14
    0.5%
    1178
    +0.12
    0.4%
    101
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1178
    +0.14
    0.08
    101
    +0.12
    0.06
    554
    +0.12
    0.06
    Negative Logits
     disreg
    -0.60
     swarovski
    -0.57
     isolato
    -0.50
     intersper
    -0.50
     disgra
    -0.49
     cowards
    -0.49
     gaily
    -0.49
     apprehen
    -0.49
     migli
    -0.49
     cushi
    -0.49
    POSITIVE LOGITS
     Trump
    1.45
    Trump
    1.41
    trump
    1.07
     trump
    0.85
    Donald
    0.82
     Donald
    0.77
     donald
    0.74
     Tr
    0.67
     trumpet
    0.67
     Trumpet
    0.66
    Activations Density 0.132%

    No Known Activations