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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 2743
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    68
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words and phrases associated with emotional connections and relationships

    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
     AssemblyCulture
    -0.79
    Personendaten
    -0.55
    sistors
    -0.51
     Paglinawan
    -0.51
    ctrons
    -0.50
     OMITBAD
    -0.49
    Sucesor
    -0.48
     smartest
    -0.48
    estacks
    -0.48
    ikusbot
    -0.47
    POSITIVE LOGITS
     feelings
    0.41
    vivencia
    0.39
     shared
    0.37
     betweenstory
    0.37
    Chham
    0.36
    ValueStyle
    0.36
    
    0.36
    Feel
    0.34
     compartir
    0.33
    feelings
    0.33
    Activations Density 0.009%

    No Known Activations