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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 5728
    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

    references to surnames and family names

    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
     Audiodateien
    -0.54
    termilk
    -0.41
    ibase
    -0.40
     fully
    -0.38
    andExpect
    -0.38
    laku
    -0.37
     recoverable
    -0.37
    Recovered
    -0.37
     recovered
    -0.37
    OCCURRED
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.64
     surnames
    0.62
     surname
    0.59
     families
    0.57
     family
    0.57
    ंदीखरीदारी
    0.50
     names
    0.50
     apellido
    0.49
    family
    0.49
     familles
    0.48
    Activations Density 0.027%

    No Known Activations