Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 5408
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    75.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to women's reproductive health and associated medical conditions

    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
    styleType
    -0.79
     فريبيس
    -0.73
     Paglinawan
    -0.72
    bootstrapcdn
    -0.68
    GOTREF
    -0.67
     oprot
    -0.64
    Personendaten
    -0.63
     OMITBAD
    -0.63
     وتسجيلات
    -0.63
    ðsíða
    -0.62
    POSITIVE LOGITS
     Mujer
    0.40
     women
    0.39
     femmes
    0.37
     féminin
    0.35
     Mujeres
    0.35
     mujeres
    0.34
     féminine
    0.34
     femenino
    0.34
    women
    0.34
     Frauen
    0.34
    Activations Density 0.002%

    No Known Activations