Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 2718
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    87
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to touch screen technology

    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
     weighs
    -0.41
     bail
    -0.41
     legal
    -0.40
     general
    -0.40
     statutory
    -0.40
     «
    -0.38
    tyimages
    -0.38
    GOTREF
    -0.38
    IDENTIFIED
    -0.38
    !*\
    -0.37
    POSITIVE LOGITS
     snippetHide
    0.52
     touchscreen
    0.50
    IContainer
    0.47
    PerformLayout
    0.46
     Touch
    0.45
    Chham
    0.45
     MotionEvent
    0.44
    Touch
    0.44
     smartphones
    0.44
     devices
    0.43
    Activations Density 0.000%

    No Known Activations