© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    traffic regulations and driving guidelines

    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
    1150
    +0.21
    0.7%
    764
    +0.15
    0.5%
    1438
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.21
    0.06
    284
    +0.15
    0.07
    1235
    +0.14
    0.06
    Negative Logits
     alkoh
    -1.09
     solidar
    -1.03
     kosme
    -0.96
     Strukt
    -0.96
     konserv
    -0.94
     geograf
    -0.93
     kollek
    -0.93
     kooper
    -0.90
     radikal
    -0.89
    Erreferentziak
    -0.89
    POSITIVE LOGITS
     anyways
    0.73
     elsewhere
    0.71
     anyway
    0.67
     afterwards
    0.67
     later
    0.65
     thereafter
    0.65
    .
    0.64
    <eos>
    0.64
     instead
    0.62
     afterward
    0.61
    Activations Density 0.956%

    No Known Activations