© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    phrases related to shared ownership and community living

    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
    1870
    +0.14
    0.4%
    1804
    +0.13
    0.4%
    2034
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    875
    +0.14
    0.05
    1314
    +0.13
    0.07
    1005
    +0.12
    0.07
    Negative Logits
    bewerken
    -0.67
     quegli
    -0.63
     scopri
    -0.62
     librement
    -0.59
     ognuno
    -0.58
     batte
    -0.58
     sappi
    -0.56
     migli
    -0.55
     volon
    -0.55
     habituellement
    -0.54
    POSITIVE LOGITS
    cipline
    0.68
    jména
    0.65
     verticales
    0.64
     pisang
    0.63
     susun
    0.61
     pama
    0.61
    +"/"+
    0.61
     silang
    0.60
     ndani
    0.59
    crapers
    0.59
    Activations Density 0.505%

    No Known Activations