© 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. 4281
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specialized and technical terms related to inventions and innovations

    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
     nawr
    -0.38
    )
    -0.37
    /
    -0.35
     theoretical
    -0.34
     switch
    -0.34
    DCHECK
    -0.34
     wood
    -0.33
     DAS
    -0.33
     gas
    -0.33
    wood
    -0.33
    POSITIVE LOGITS
    GEBURTSDATUM
    0.73
     kasarigan
    0.68
    AsUp
    0.65
     defaultstate
    0.64
    ंदीखरीदारी
    0.64
     AssemblyCompany
    0.57
     noDo
    0.57
    LEGGI
    0.57
     ſeine
    0.56
    
    0.56
    Activations Density 3.114%

    No Known Activations