© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing regulations or guidelines

    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
    +0.22
    0.7%
    1334
    +0.10
    0.3%
    1705
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.22
    0.06
    1334
    +0.10
    0.05
    16
    +0.10
    0.06
    Negative Logits
     legais
    -0.62
    cần
    -0.59
    )>=
    -0.58
     noastră
    -0.55
    ='';
    -0.55
     månader
    -0.54
     femininos
    -0.54
     prácti
    -0.54
     oamen
    -0.54
    Formazione
    -0.54
    POSITIVE LOGITS
     pican
    0.66
     Jä
    0.64
     teras
    0.64
     augus
    0.63
     marron
    0.61
     kac
    0.60
     Teg
    0.59
     lele
    0.59
     Gén
    0.58
     bahia
    0.58
    Activations Density 0.249%

    No Known Activations