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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 4732
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    64.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    elements related to user interface design and layout characteristics

    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
    WriteTagHelper
    -0.59
    NamedQuery
    -0.47
    Personendaten
    -0.46
     nieruch
    -0.43
    HttpFoundation
    -0.42
     meisten
    -0.42
    httphttps
    -0.42
    ⎨
    -0.42
     Audiodateien
    -0.41
    ruik
    -0.41
    POSITIVE LOGITS
    IContainer
    0.44
    IntoConstraints
    0.44
     designers
    0.44
     spatial
    0.43
    RenderAtEndOf
    0.43
     diseñadores
    0.42
    TypedDataSet
    0.41
    Chham
    0.40
     initComponents
    0.40
     interface
    0.40
    Activations Density 0.131%

    No Known Activations