© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 256
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases involving personal opinions or reflections

    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
     nawr
    -0.42
    interopRequire
    -0.40
     hakim
    -0.39
    kunta
    -0.38
    Literatur
    -0.37
    UpInside
    -0.37
     manuals
    -0.36
     taha
    -0.36
     Wylie
    -0.35
    RTEE
    -0.35
    POSITIVE LOGITS
    ſelf
    0.51
     '\\;'
    0.49
     ErrIntOverflow
    0.48
     purpoſe
    0.48
    ſelves
    0.47
     leaſt
    0.44
    addOn
    0.43
    ">//
    0.43
    LEGGI
    0.42
    คลิ
    0.42
    Activations Density 2.304%

    No Known Activations