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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 1172
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    sentences that express strong emotions or sentiments

    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
    ikusbot
    -0.62
    GEBURTSDATUM
    -0.58
    estacks
    -0.57
    WriteTagHelper
    -0.57
     Audiodateien
    -0.57
    tanleria
    -0.55
    $_['
    -0.55
    Hauptartikel
    -0.55
     allAfrica
    -0.54
    Personendaten
    -0.54
    POSITIVE LOGITS
    ValueStyle
    0.38
     I
    0.35
    
    0.35
    efois
    0.35
     people
    0.33
     might
    0.33
    zä
    0.32
     élo
    0.31
     shared
    0.31
    personal
    0.30
    Activations Density 0.010%

    No Known Activations