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. 11098
    Prev
    Next
    INDEX
    Explanations

    biology and medicine

    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
     resourceCulture
    -0.50
    Cyfeiriadau
    -0.50
     "..\..\
    -0.49
     مشين
    -0.49
     geweest
    -0.47
     TestBed
    -0.47
    ußen
    -0.46
    upol
    -0.44
    
    -0.43
    saida
    -0.41
    POSITIVE LOGITS
    SignOut
    0.56
    Reducers
    0.55
     Nul
    0.54
     onCancelled
    0.54
     ZS
    0.53
     Siegfried
    0.52
    andle
    0.51
     hippocampal
    0.51
     blockade
    0.51
     Cæsar
    0.51
    Activations Density 0.114%

    No Known Activations