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. 5235
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    80.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to legal terms related to prosecution

    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
    styleType
    -0.77
    bootstrapcdn
    -0.61
     Audiodateien
    -0.54
     lizenzfreies
    -0.52
     Picchu
    -0.52
    Kariera
    -0.51
     esternos
    -0.51
     ویکی‌پدیای
    -0.50
    出版年
    -0.50
    zheimer
    -0.49
    POSITIVE LOGITS
     judiciaire
    0.41
     proceedings
    0.41
    ActivityCompat
    0.41
    FormState
    0.40
     proceeding
    0.39
     Proceedings
    0.38
     épreuve
    0.37
     judicia
    0.36
    PerformLayout
    0.36
    ValueStyle
    0.35
    Activations Density 0.000%

    No Known Activations