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. 12910
    Prev
    Next
    INDEX
    Explanations

    scientific/medical research

    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
    กัน
    -0.49
    schule
    -0.45
    lor
    -0.44
    τες
    -0.44
    vile
    -0.43
    dale
    -0.43
    lass
    -0.43
    wix
    -0.42
    λοι
    -0.42
    Prototype
    -0.41
    POSITIVE LOGITS
     poffe
    0.81
     Monfieur
    0.77
    ContentAsync
    0.75
     ſeveral
    0.73
    jspx
    0.73
     poffible
    0.73
     perfons
    0.72
    actionMode
    0.71
     متعلقه
    0.71
     himſelf
    0.71
    Activations Density 0.010%

    No Known Activations