© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44217
    Prev
    Next
    INDEX
    Explanations

    that

    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
     propOrder
    -1.31
     démocr
    -1.30
     that
    -1.29
     enfans
    -1.28
    that
    -1.27
     itſelf
    -1.27
     auffi
    -1.23
     kwamba
    -1.16
     ainfi
    -1.16
     chré
    -1.14
    POSITIVE LOGITS
     is
    1.26
     we
    1.13
     the
    1.08
     can
    1.07
     it
    1.05
    ,
    0.94
     will
    0.93
     there
    0.91
     are
    0.88
     was
    0.88
    Activations Density 0.455%

    No Known Activations