© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 2393
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    91.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    code elements related to access modifiers and variable naming conventions

    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
    ChildScrollView
    -0.59
    WriteTagHelper
    -0.44
     Audiodateien
    -0.44
     Stoppers
    -0.44
    tagext
    -0.41
    MessageOf
    -0.41
     muualla
    -0.40
    arschijnlijk
    -0.40
    WireFormatLite
    -0.39
     zufolge
    -0.39
    POSITIVE LOGITS
    protected
    0.60
    XmlAccessType
    0.60
     secret
    0.57
    private
    0.57
     private
    0.56
    secret
    0.56
     privacy
    0.51
    guarded
    0.51
     protected
    0.49
     PRIVATE
    0.49
    Activations Density 0.146%

    No Known Activations