© 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. 7112
    Prev
    Next
    INDEX
    Explanations

    phrases related to desalination and water resource management

    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
    1120
    +0.18
    0.6%
    939
    +0.12
    0.4%
    1499
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.18
    0.06
    1499
    +0.12
    0.06
    5
    +0.12
    0.04
    Negative Logits
     racon
    -0.74
     emphat
    -0.67
    ;;)
    -0.65
     minimalis
    -0.64
     violences
    -0.61
     nadru
    -0.60
     tempel
    -0.60
     applau
    -0.59
     logis
    -0.59
     vocale
    -0.59
    POSITIVE LOGITS
     water
    0.92
    water
    0.69
     groundwater
    0.68
     Water
    0.68
     irrigation
    0.66
    Water
    0.65
     rainwater
    0.64
     waters
    0.61
     WATER
    0.61
     drainage
    0.59
    Activations Density 0.510%

    No Known Activations