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. 4-CLT-HP
    4. 4227
    Prev
    Next
    INDEX
    Explanations

    of

    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
     насељу
    -0.72
    AccessorTable
    -0.71
     esperienze
    -0.65
     amitié
    -0.64
     réfugi
    -0.62
    AndEndTag
    -0.62
    FromNib
    -0.62
     EconPapers
    -0.62
     protoimpl
    -0.60
    ükemmel
    -0.60
    POSITIVE LOGITS
    __(/*!
    0.61
    podar
    0.48
    setViewportView
    0.47
    isait
    0.46
    dote
    0.45
    전히
    0.45
     to
    0.44
    atoga
    0.43
    asable
    0.43
    都要
    0.43
    Activations Density 0.004%

    No Known Activations