© 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
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 4462
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    75.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various forms of the word "blend" or "mixture."

    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
    httphttps
    -0.62
     Paglinawan
    -0.61
    bewerken
    -0.58
    Personendaten
    -0.56
     Référence
    -0.55
    äsident
    -0.55
     Audiodateien
    -0.54
    arangay
    -0.54
    出版年
    -0.54
     Wicidata
    -0.53
    POSITIVE LOGITS
     mixture
    0.76
     mixed
    0.71
     mezcla
    0.69
     mix
    0.68
     blend
    0.66
     MIX
    0.66
     mistura
    0.66
     mixing
    0.64
     mélang
    0.61
     mixtures
    0.60
    Activations Density 0.000%

    No Known Activations