© 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. 160
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    47.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    legal terminology and concepts related to compliance and responsibilities

    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
    -0.35
    Geographie
    -0.35
    MessageOf
    -0.34
     AssemblyCulture
    -0.34
     wypo
    -0.33
    ChildScrollView
    -0.32
    WriteTagHelper
    -0.32
    
    -0.32
     }));
    -0.32
     direto
    -0.32
    POSITIVE LOGITS
    setVerticalGroup
    0.77
     propOrder
    0.59
    basicConfig
    0.56
    ſo
    0.56
     ſtand
    0.56
    ftance
    0.53
     purpoſe
    0.53
    ſelves
    0.51
     myſelf
    0.50
     Infórmanos
    0.49
    Activations Density 7.247%

    No Known Activations