© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14559
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in 'ened' that describe a sense of authority or importance

    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
    890
    +0.11
    0.4%
    1053
    +0.11
    0.4%
    1271
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.11
    0.03
    1413
    +0.11
    0.02
    1892
    +0.10
    0.02
    Negative Logits
     envelo
    -0.82
     véhic
    -0.78
     déchir
    -0.77
     génér
    -0.76
     gouver
    -0.75
     éc
    -0.74
     apprehen
    -0.73
     compréhen
    -0.72
     renou
    -0.71
     exag
    -0.70
    POSITIVE LOGITS
     bold
    1.14
     courage
    1.10
     courageous
    1.08
     brave
    1.07
    bold
    1.04
     daring
    0.98
     dared
    0.94
    Bold
    0.93
     Bold
    0.92
     dare
    0.92
    Activations Density 0.110%

    No Known Activations