© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 3064
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    74
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases related to costs and expenditures

    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
    -0.76
    :✨
    -0.58
     Audiodateien
    -0.48
    estacks
    -0.47
    WriteTagHelper
    -0.46
     SYLLABLE
    -0.46
     homoto
    -0.43
     bluetooth
    -0.43
    httphttps
    -0.43
    instancetype
    -0.43
    POSITIVE LOGITS
    Cost
    0.67
     costs
    0.65
    price
    0.64
     cost
    0.64
     pricing
    0.64
     price
    0.63
    cost
    0.60
     costos
    0.60
    costs
    0.58
     Cost
    0.57
    Activations Density 0.096%

    No Known Activations