© 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. 778
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, and compliance

    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
    1245
    +0.08
    0.2%
    674
    +0.08
    0.2%
    1809
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1847
    +0.08
    0.03
    2044
    +0.08
    0.07
    725
    +0.07
    0.02
    Negative Logits
     trovar
    -0.52
     dimenti
    -0.50
     interessa
    -0.49
     credere
    -0.48
     abbra
    -0.46
     parlar
    -0.44
     Résultats
    -0.44
     scopri
    -0.44
    coration
    -0.44
    المشاركات
    -0.43
    POSITIVE LOGITS
     but
    1.70
    but
    1.54
     nhưng
    1.41
     BUT
    1.33
    But
    1.29
     But
    1.25
     pero
    1.22
    BUT
    1.21
     แต่
    1.04
     tetapi
    1.01
    Activations Density 0.827%

    No Known Activations