© 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. 4276
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    55.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various forms and occurrences of punctuation marks

    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
     nawr
    -0.44
    Geographie
    -0.40
     hakim
    -0.39
     vapour
    -0.39
    äsident
    -0.37
    instancetype
    -0.36
    ropoda
    -0.36
     outlawed
    -0.36
    rousel
    -0.36
     taha
    -0.36
    POSITIVE LOGITS
     exchange
    0.52
    exchange
    0.48
     exchanges
    0.46
     Exchange
    0.45
    +#+#
    0.45
     EXCHANGE
    0.45
     Infórmanos
    0.44
    
    0.44
    bibfield
    0.44
    Exchange
    0.44
    Activations Density 1.699%

    No Known Activations