© 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. 1926
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    67.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    keywords related to socket programming and network connections

    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
    assertRaises
    -0.32
     
    -0.31
    很简单
    -0.30
     Paglinawan
    -0.30
     bijzonder
    -0.29
     ）
    -0.28
    évaluation
    -0.28
     évaluations
    -0.28
     be
    -0.27
     easy
    -0.27
    POSITIVE LOGITS
     sockets
    0.72
     socket
    0.71
     Socket
    0.69
    LookAnd
    0.68
    socket
    0.66
    ſelves
    0.65
    хьтан
    0.65
     itſelf
    0.64
    transQ
    0.64
    Socket
    0.63
    Activations Density 0.734%

    No Known Activations