© 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. 4076
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    75.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases related to health and wellness care

    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
     ***!
    -0.49
     recombination
    -0.47
     Elasticity
    -0.46
     Instability
    -0.46
    arif
    -0.46
     Paglinawan
    -0.46
     magnet
    -0.45
     kaban
    -0.45
    bacter
    -0.45
     Replaced
    -0.45
    POSITIVE LOGITS
    fromnode
    0.40
    +#+#
    0.37
     enfoque
    0.36
     beginnetje
    0.36
     léč
    0.36
    IContainer
    0.36
    rrggbb
    0.35
     soins
    0.35
     intervenciones
    0.35
     trabajo
    0.34
    Activations Density 0.007%

    No Known Activations