© 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. 4588
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    53.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and special characters in sentences

    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
     recognised
    -0.42
     adulte
    -0.35
    סף
    -0.35
     recognized
    -0.35
    culada
    -0.33
    rousel
    -0.33
     adulta
    -0.32
     hakim
    -0.32
    )
    -0.32
     taha
    -0.31
    POSITIVE LOGITS
     '\\;'
    0.71
     betweenstory
    0.69
     noDo
    0.67
    principalTable
    0.65
    ſelf
    0.65
     purpoſe
    0.65
    +#+#
    0.63
     ſtand
    0.62
    
    0.62
    fromnode
    0.60
    Activations Density 1.193%

    No Known Activations