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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31044
    Prev
    Next
    INDEX
    Explanations

    the word "primer" and variants of it

    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
    nonatomic
    -0.72
     &___
    -0.68
    BeginContext
    -0.66
    //
    -0.65
     sweets
    -0.64
    GenerationType
    -0.63
     ziren
    -0.63
     pliers
    -0.63
    ventus
    -0.63
    Switcher
    -0.62
    POSITIVE LOGITS
     Primer
    1.20
    Primer
    1.19
     PRIMER
    1.10
     primer
    1.08
    primer
    0.93
    PRIMER
    0.78
     Ό
    0.72
    έχ
    0.71
    nettes
    0.69
     jPanel
    0.68
    Activations Density 0.002%

    No Known Activations