© 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. 2598
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    33.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and formatting symbols

    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
    httphttps
    -0.55
     sostenibilidad
    -0.39
    Населення
    -0.37
    Zunanje
    -0.36
     particuliers
    -0.36
     particulier
    -0.35
    ยิ่ง
    -0.34
     gerekti
    -0.32
     individuos
    -0.32
     entendimiento
    -0.32
    POSITIVE LOGITS
     queſta
    0.77
     purpoſe
    0.76
     surla
    0.76
     propOrder
    0.75
     ſind
    0.70
     MessageBoxIcon
    0.69
     useCallback
    0.69
    ="@+
    0.67
     raiſ
    0.66
     onPostExecute
    0.66
    Activations Density 3.524%

    No Known Activations