© 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. 4353
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    63
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of the word "praise."

    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
     Audiodateien
    -0.55
    Personendaten
    -0.52
     AssemblyCulture
    -0.47
    jsxFileName
    -0.47
    $_['
    -0.45
    HttpFoundation
    -0.43
    MessageOf
    -0.43
     deus
    -0.42
    httphttps
    -0.42
    ERVIEW
    -0.42
    POSITIVE LOGITS
     award
    0.57
     awards
    0.57
     praise
    0.54
     recognition
    0.52
     Anerkennung
    0.52
     praised
    0.52
    awards
    0.51
     accolades
    0.51
     reconhecimento
    0.51
     acknowledgment
    0.51
    Activations Density 0.000%

    No Known Activations