© 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. 14479
    Prev
    Next
    INDEX
    Explanations

    phrases related to power dynamics and political rhetoric

    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
    604
    +0.10
    0.3%
    1129
    +0.08
    0.2%
    1851
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.05
    1851
    +0.08
    0.04
    963
    +0.07
    0.04
    Negative Logits
     increa
    -1.98
     disagre
    -1.93
     milf
    -1.88
     strick
    -1.87
     encomp
    -1.85
     maneu
    -1.85
     impra
    -1.84
     reluct
    -1.84
     excru
    -1.83
     inev
    -1.83
    POSITIVE LOGITS
     suddenly
    0.96
     lại
    0.75
    かわらず
    0.74
     yet
    0.72
     somehow
    0.66
    Suddenly
    0.65
     plötzlich
    0.65
    IsContent
    0.65
     still
    0.64
    endphp
    0.64
    Activations Density 0.473%

    No Known Activations