© 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. 3635
    Prev
    Next
    INDEX
    Explanations

    words related to vague or uncertain concepts

    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
    1896
    +0.15
    0.5%
    1265
    +0.14
    0.4%
    468
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.15
    0.04
    1363
    +0.14
    0.03
    1896
    +0.13
    0.02
    Negative Logits
     depic
    -0.81
     compen
    -0.78
     coloré
    -0.77
     shenan
    -0.75
     intersper
    -0.74
     increa
    -0.72
     imprimé
    -0.71
     typique
    -0.71
     Diction
    -0.71
     reluct
    -0.70
    POSITIVE LOGITS
     vague
    0.82
     unclear
    0.68
     blurry
    0.64
     ambiguous
    0.62
     hazy
    0.61
    quarelle
    0.57
     blurred
    0.56
     yogur
    0.55
     vagas
    0.54
     fuzzy
    0.54
    Activations Density 0.193%

    No Known Activations