© 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. 91080
    Prev
    Next
    INDEX
    Explanations

    two

    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
    two
    -1.81
    Two
    -1.71
     two
    -1.43
     deux
    -1.35
    TWO
    -1.32
     Two
    -1.27
     δύο
    -1.17
     två
    -1.12
     TWO
    -1.11
     două
    -1.09
    POSITIVE LOGITS
    -
    0.68
     or
    0.67
     to
    0.63
     different
    0.59
     of
    0.57
     more
    0.56
     dozen
    0.55
     and
    0.54
     other
    0.52
     types
    0.49
    Activations Density 0.024%

    No Known Activations