© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6966
    Prev
    Next
    INDEX
    Explanations

    references to electric vehicles (EVs) and related topics like battery storage and emissions

    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
    1385
    +0.15
    0.4%
    1356
    +0.12
    0.4%
    1842
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    942
    +0.15
    0.03
    1048
    +0.12
    0.01
    1356
    +0.10
    0.02
    Negative Logits
     isuzu
    -0.76
     theolog
    -0.75
     cabrio
    -0.75
     chrysler
    -0.74
     hilux
    -0.72
     shimano
    -0.66
     peugeot
    -0.66
    {?>
    -0.64
     piaggio
    -0.62
     renault
    -0.61
    POSITIVE LOGITS
     electric
    0.65
     emissions
    0.59
     emission
    0.56
     battery
    0.54
     technologies
    0.53
     conftest
    0.52
     hybrid
    0.51
    retrofit
    0.50
     Uptake
    0.49
     technology
    0.48
    Activations Density 0.174%

    No Known Activations