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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 6051
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    54.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to regular expressions in code-related contexts

    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
     vindo
    -0.35
    __).
    -0.34
    — 
    -0.32
     himo
    -0.30
    tagext
    -0.29
    <bos>
    -0.29
     Brito
    -0.28
     przysz
    -0.28
    xodo
    -0.28
     transmisión
    -0.27
    POSITIVE LOGITS
     Administrativna
    0.78
     regex
    0.60
     Италијани
    0.59
     Taktlose
    0.55
     geweſen
    0.55
    <tfoot>
    0.54
    <unused14>
    0.54
    Regex
    0.54
     RegExp
    0.54
    IntoConstraints
    0.54
    Activations Density 2.459%

    No Known Activations