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-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31351
    Prev
    Next
    INDEX
    Explanations

    the words "prisoner" and "inmate"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    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
     Geschmack
    -0.77
     scl
    -0.74
    исленность
    -0.74
     发表于
    -0.73
     يول
    -0.72
    LLocation
    -0.70
    __);
    -0.69
     MCS
    -0.69
     Hok
    -0.69
     Tilly
    -0.69
    POSITIVE LOGITS
     prisoner
    0.65
     inmate
    0.63
     inmates
    0.61
    IBAction
    0.61
     Prisoner
    0.60
    ubscribe
    0.59
     חיצוניים
    0.56
    RenderAtEndOf
    0.56
     دار
    0.55
     prisoners
    0.55
    Activations Density 0.009%

    No Known Activations