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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91256
    Prev
    Next
    INDEX
    Explanations

    and/or

    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
     and
    -0.95
     is
    -0.68
     to
    -0.61
     will
    -0.61
    to
    -0.60
     was
    -0.60
     are
    -0.59
     refers
    -0.59
    TagHelper
    -0.59
     should
    -0.58
    POSITIVE LOGITS
     '\\;'
    0.75
     protoimpl
    0.71
    ,
    0.71
    verwijspagina
    0.69
    tvguidetime
    0.69
    hoeddwyd
    0.68
     @"/
    0.66
     تضيفلها
    0.65
    Personensuche
    0.64
    хьтан
    0.63
    Activations Density 0.337%

    No Known Activations