Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    54
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases that indicate conclusions, assertions, or the ends of thoughts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nawr
    -0.35
    Geographie
    -0.34
    gemeinden
    -0.32
    )
    -0.32
     baratos
    -0.31
     revenu
    -0.30
    Request
    -0.29
     hoga
    -0.29
    wayat
    -0.29
    Smarty
    -0.29
    POSITIVE LOGITS
     purpoſe
    0.65
     kasarigan
    0.60
    ſelf
    0.60
     betweenstory
    0.60
    InstrumentedTest
    0.59
    Manbalar
    0.57
    +#+#
    0.56
    RTCK
    0.56
    Хьажоргаш
    0.56
    ſelves
    0.56
    Act Density 1.832%

    No Known Activations