© 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. 103
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    93.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to cows and animals in a coding context

    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
    WriteTagHelper
    -0.47
     screwed
    -0.43
    ถ
    -0.42
    BagLayout
    -0.41
     Paglinawan
    -0.41
    uerre
    -0.41
    ugget
    -0.40
     opar
    -0.40
    TableId
    -0.39
     hisz
    -0.39
    POSITIVE LOGITS
    Animals
    0.70
     animals
    0.69
     Animals
    0.68
    animals
    0.68
    animal
    0.59
     animale
    0.58
     ANIMALS
    0.58
    Animal
    0.56
     animales
    0.55
     animaux
    0.54
    Activations Density 0.000%

    No Known Activations