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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 744
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    70.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    actions related to user interface interactions, specifically clicking on links or fields

    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
    WriteTagHelper
    -0.40
     Rechnung
    -0.38
    '''
    -0.38
     theoretical
    -0.38
    ]]=
    -0.38
    EMBER
    -0.37
     umumnya
    -0.37
     principally
    -0.36
     {?
    -0.36
     general
    -0.35
    POSITIVE LOGITS
    Хьажоргаш
    0.66
     clicks
    0.64
     clicking
    0.61
     cliquer
    0.56
    Chham
    0.55
    clicking
    0.55
     click
    0.54
    ьажоргаш
    0.54
    fromnode
    0.54
     scrolling
    0.53
    Activations Density 0.000%

    No Known Activations