© 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
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 4431
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    73
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms emphasizing significance or importance

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.75
    estacks
    -0.70
    LabelTagHelper
    -0.69
    ViewImports
    -0.66
     IFTT
    -0.66
     ✭✭
    -0.64
     <>",
    -0.63
    WriteTagHelper
    -0.62
    ➟
    -0.61
     Doctrine
    -0.58
    POSITIVE LOGITS
     especially
    1.00
    especially
    0.81
    Especially
    0.81
     Especially
    0.78
     particularly
    0.77
     especialmente
    0.72
     zwłaszcza
    0.70
     особенно
    0.68
     szczególnie
    0.64
     особли
    0.61
    Activations Density 0.003%

    No Known Activations