© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 3486
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    47.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to user interface elements and dialog management

    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
     translateY
    -0.40
    WriteTagHelper
    -0.38
     pungkas
    -0.34
     Audiodateien
    -0.33
    WritableDatabase
    -0.31
     parlamentar
    -0.30
     katanya
    -0.30
    apimachinery
    -0.29
    hawatir
    -0.28
     wissenschaft
    -0.27
    POSITIVE LOGITS
    +#+#
    0.67
     يتيمه
    0.59
    ंदीखरीदारी
    0.59
     EnglishChoose
    0.59
    ialog
    0.58
    ﹧
    0.58
    <unused1>
    0.56
    <unused53>
    0.56
    ⸄
    0.56
    <pad>
    0.56
    Activations Density 0.001%

    No Known Activations