© 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. 989
    Prev
    Next
    INDEX
    Explanations

    but

    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
     but
    -1.90
     tetapi
    -1.60
    but
    -1.41
     pero
    -1.40
     namun
    -1.31
     entanto
    -1.29
     nhưng
    -1.23
     mutta
    -1.20
     αλλά
    -1.16
     maar
    -1.14
    POSITIVE LOGITS
     the
    0.99
     it
    0.91
     there
    0.83
     this
    0.79
     they
    0.77
     you
    0.76
     their
    0.68
     these
    0.67
     your
    0.66
     we
    0.65
    Activations Density 0.143%

    No Known Activations