Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 703
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    84.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to privacy and protected entities in programming 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
    ChildScrollView
    -0.39
     gerais
    -0.39
     země
    -0.37
     eleições
    -0.36
    tagext
    -0.36
     Stoppers
    -0.36
     geluk
    -0.35
     Instrumente
    -0.35
    kháu
    -0.34
     Italij
    -0.34
    POSITIVE LOGITS
     PRIVATE
    0.79
     private
    0.77
    private
    0.77
    Private
    0.75
     Private
    0.74
     Priv
    0.69
    PRIVATE
    0.69
    secret
    0.67
    Priv
    0.63
     secret
    0.63
    Activations Density 0.006%

    No Known Activations