© 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. 4307
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    57.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    sentences with specific punctuation or formatting elements

    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
    -0.36
     recognised
    -0.34
    tructor
    -0.33
     adulte
    -0.32
    ėte
    -0.32
     mily
    -0.31
     histórica
    -0.31
     vapour
    -0.30
     Herrn
    -0.29
     revenu
    -0.29
    POSITIVE LOGITS
     betweenstory
    0.63
    ########.
    0.59
    ंदीखरीदारी
    0.57
     queſta
    0.57
     насељу
    0.56
    setVerticalGroup
    0.55
    UserScript
    0.53
     purpoſe
    0.53
     '\\;'
    0.52
    ViewInit
    0.51
    Activations Density 1.531%

    No Known Activations