© 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. 2580
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    74.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific locations or structures related to water transportation

    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
    /*++
    -0.42
    zheimer
    -0.39
     tiên
    -0.38
    </thead>
    -0.38
    djangoproject
    -0.38
     dominant
    -0.37
    UTIVE
    -0.37
     тради
    -0.36
    HttpFoundation
    -0.36
    moga
    -0.35
    POSITIVE LOGITS
    IntoConstraints
    0.62
    LookAnd
    0.57
    fromnode
    0.55
    ValueStyle
    0.54
     EconPapers
    0.54
    Билгалдахарш
    0.51
     typelib
    0.51
    EndGlobalSection
    0.50
    Geplaatst
    0.49
     للمعارف
    0.49
    Activations Density 0.000%

    No Known Activations