© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4409
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    76
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to Donald Trump and his tweets

    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
    instancetype
    -0.36
    cuela
    -0.32
    andExpect
    -0.32
     grund
    -0.31
    bildēt
    -0.30
     beker
    -0.30
    HttpFoundation
    -0.30
    asteroido
    -0.30
     itinéraires
    -0.30
     Nadel
    -0.29
    POSITIVE LOGITS
     Trump
    0.70
    PerformLayout
    0.64
    Trump
    0.62
     estekak
    0.62
     незавершена
    0.55
    特朗普
    0.53
    Obama
    0.53
    TypedDataSet
    0.50
    enumii
    0.50
    ########.
    0.50
    Activations Density 0.001%

    No Known Activations