© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14686
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgency and timeliness

    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
    2034
    +0.13
    0.4%
    1013
    +0.11
    0.3%
    1110
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.13
    0.05
    284
    +0.11
    0.05
    1013
    +0.08
    0.05
    Negative Logits
    Cześć
    -0.74
    Sklici
    -0.71
    Glej
    -0.70
    você
    -0.70
     Voyez
    -0.69
     honnête
    -0.67
    Bardzo
    -0.67
    Zunanje
    -0.66
    Dziękuję
    -0.65
    glLoad
    -0.65
    POSITIVE LOGITS
    aneity
    0.57
     (<
    0.55
     kaos
    0.55
     optik
    0.54
     teater
    0.53
     akut
    0.50
     chaises
    0.50
    ïe
    0.49
     without
    0.48
     herbes
    0.48
    Activations Density 0.292%

    No Known Activations