© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4314
    Prev
    Next
    INDEX
    Explanations

    political and legislative terms

    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
    1042
    +0.12
    0.4%
    2034
    +0.11
    0.3%
    690
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.12
    0.04
    1210
    +0.11
    0.03
    1792
    +0.09
    0.04
    Negative Logits
     dises
    -1.14
     cyr
    -1.11
     ordina
    -1.11
     robus
    -1.09
     inder
    -1.09
     dispen
    -1.09
     istr
    -1.08
     curi
    -1.05
     diabe
    -1.04
     solidar
    -1.04
    POSITIVE LOGITS
     will
    1.02
    will
    0.86
     would
    0.77
     Will
    0.73
     sẽ
    0.69
     hopefully
    0.69
     may
    0.67
     then
    0.66
     could
    0.66
    Will
    0.66
    Activations Density 0.214%

    No Known Activations