© 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. 13293
    Prev
    Next
    INDEX
    Explanations

    environmental and ecological 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
    752
    +0.10
    0.3%
    1703
    +0.09
    0.3%
    1385
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    942
    +0.10
    0.05
    939
    +0.09
    0.05
    305
    +0.08
    0.04
    Negative Logits
     logitech
    -0.75
     geforce
    -0.64
     ritard
    -0.63
     didac
    -0.61
     indoc
    -0.60
     Komunikasi
    -0.59
     nadru
    -0.59
     hasbro
    -0.59
     shenan
    -0.57
     excru
    -0.56
    POSITIVE LOGITS
     ecosystems
    0.71
     planet
    0.65
     biodiversity
    0.63
     Earth
    0.61
     earth
    0.60
     environment
    0.58
     ecosystem
    0.57
     sustainable
    0.57
     resources
    0.56
     environmental
    0.56
    Activations Density 0.441%

    No Known Activations