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. 1-CLT-HP
    4. 11022
    Prev
    Next
    INDEX
    Explanations

    supporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supporting
    -0.53
    supporting
    -0.53
     Supporting
    -0.51
    rungsseite
    -0.47
     ocurrió
    -0.44
     pendukung
    -0.43
     ellers
    -0.43
     supported
    -0.42
    ine
    -0.42
    のでしょう
    -0.41
    POSITIVE LOGITS
    IUrlHelper
    0.69
    WAUKEE
    0.65
    Попис
    0.63
    ragalactic
    0.63
    twimg
    0.63
    RTLD
    0.61
    mpty
    0.61
    InitStruct
    0.61
    InitVars
    0.60
    MockMvc
    0.59
    Activations Density 0.008%

    No Known Activations