© 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. 4391
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    53
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    personal reflections and experiences

    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
    Personendaten
    -0.57
    WriteTagHelper
    -0.57
     AssemblyCulture
    -0.56
    AddTagHelper
    -0.56
    лтемелер
    -0.56
    ❉
    -0.49
    httphttps
    -0.48
     preventative
    -0.47
     intptr
    -0.47
     recoverable
    -0.47
    POSITIVE LOGITS
     myself
    0.59
     I
    0.47
    myself
    0.46
     sentía
    0.41
    เอง
    0.39
    personal
    0.38
    Myself
    0.38
    feels
    0.38
    รู้สึก
    0.38
    feel
    0.38
    Activations Density 0.001%

    No Known Activations